diff --git a/docs/Timbl_6.4_Manual.pdf b/docs/Timbl_6.4_Manual.pdf deleted file mode 100644 index fcbbfd0..0000000 Binary files a/docs/Timbl_6.4_Manual.pdf and /dev/null differ diff --git a/docs/Timbl_7.0_Manual.pdf b/docs/Timbl_7.0_Manual.pdf new file mode 100644 index 0000000..ffc6dc0 Binary files /dev/null and b/docs/Timbl_7.0_Manual.pdf differ diff --git a/docs/texfiles/Timbl_6.4_Manual.tex b/docs/texfiles/Timbl_7.0_Manual.tex similarity index 91% rename from docs/texfiles/Timbl_6.4_Manual.tex rename to docs/texfiles/Timbl_7.0_Manual.tex index 94a9ed2..6dd03a4 100644 --- a/docs/texfiles/Timbl_6.4_Manual.tex +++ b/docs/texfiles/Timbl_7.0_Manual.tex @@ -1,4 +1,4 @@ -% TiMBL 6.4 manual +% TiMBL 7.0 manual \documentclass{book} @@ -9,28 +9,26 @@ \usepackage{fullname} \usepackage{url} +% allow long URLs to break across lines +\urldef{\timblmanualurl}\url{https://github.com/LanguageMachines/timbl/blob/master/docs/Timbl_7.0_Manual.pdf} + \newcommand{\chisq}{{$ \chi^2 $}} \author{Walter Daelemans$*$ \and Jakub Zavrel$\dagger$ \and Ko van der Sloot$\dagger\dagger$\\ \and - Antal van den Bosch$\dagger\dagger$\\ \ \\ + Antal van den Bosch$\ddagger$\\ \ \\ (*) CLiPS - Computational Linguistics Group\\ Department of Linguistics \\ University of Antwerp\\ \\ - ($\dagger$) Textkernel B.V.\\ \\ -% (**) Induction of Linguistic Knowledge Research Group\\ -% Tilburg center for Cognition and Communication \\ -% Tilburg University \\ \\ + ($\dagger$) Zeta Alpha\\ \\ ($\dagger\dagger$) Centre for Language Studies \\ Radboud University Nijmegen \\ \\ - URL: http://ilk.uvt.nl\thanks{This document is available from - http://ilk.uvt.nl/downloads/pub/papers/ilk.XXXX.pdf. All rights reserved - Centre for Language Studies, Nijmegen \ - Induction of Linguistic Knowledge, Tilburg University and - CLiPS, University of Antwerp.}} + ($\ddagger$) Faculty of Humanities \\ + Utrecht University \\ \\ + URL: https://languagemachines.github.io/timbl\thanks{This document is available from + \timblmanualurl.}} \title{{\huge TiMBL: Tilburg Memory-Based Learner} \\ \vspace*{0.5cm} -{\bf version 6.4} \\ \vspace*{0.5cm}{\huge Reference Guide}\\ -\vspace*{1cm} {\it ILK Technical Report -- ILK 11-01}} +{\bf version 7.0} \\ \vspace*{0.5cm}{\huge Reference Guide}} %better paragraph indentation \parindent 0pt @@ -101,7 +99,7 @@ \chapter*{Preface} to it immensely by giving us feedback and reporting bugs, and to the two organisations that have supported and enabled its development: NWO, the Netherlands Organization for Scientific Research, and the -School of Humanities of Tilburg University. NWO funding has spanned +Tilburg School for Humanities and Digital Sciences. NWO funding has spanned three subsequent periods totalling fourteen years. From 1997 until 2001 development was part of the ``Induction of Linguistic Knowledge'' research project funded by NWO's {\em Pionier}\/ programme. Between @@ -110,17 +108,19 @@ \chapter*{Preface} programme, and between 2006 and 2011 as part of the ``Implicit Linguistics'' research project under the NWO Vici programme. -The current release (version 6.4) coincides with a release of a Debian -Science package for TiMBL. Its most significant change is a -multiprocessor option that ``clones'' TiMBL internally so that it can -classify a test set on $n$ available processors. An elaborate -description of the changes from version 1.0 up to 6.4 can be found in -Chapter~\ref{changes}. Although all new features have been tested for +The current release (version 7.0) is the result of a long series of +incremental releases since version 6.4, which together brought, among +other things, a multiprocessor option that ``clones'' TiMBL internally +so that it can classify a test set on $n$ available processors, +improved Unicode/UTF-8 handling, and a number of new options. An +elaborate description of the changes from version 1.0 up to 7.0 can be +found in Chapter~\ref{changes}. Although all new features have been +tested for some time in our research groups, the software may still contain bugs and inconsistencies in some places. We would appreciate it if you would send bug reports, ideas about enhancements of the software and -the manual, and any other comments you might have, to {\tt - Timbl@uvt.nl}. +the manual, and any other comments you might have, to our issue +tracker at \url{https://github.com/LanguageMachines/timbl/issues}. This reference guide is structured as follows. In Chapter~\ref{license} you can find the terms of the open source @@ -156,56 +156,72 @@ \chapter{GNU General Public License} You should have received a copy of the GNU General Public License along with TiMBL. If not, see $<$http://www.gnu.org/licenses/$>$. -In publication of research that makes use of TiMBL 6.4, a citation +In publication of research that makes use of TiMBL 7.0, a citation should be given of: {\em ``Walter Daelemans, Jakub Zavrel, Ko van der - Sloot, and Antal van den Bosch (2012). TiMBL: Tilburg Memory Based - Learner, version 6.4, Reference Guide. ILK Technical Report XX-XX + Sloot, and Antal van den Bosch (2026). TiMBL: Tilburg Memory Based + Learner, version 7.0, Reference Guide. Available from \\ {\tt - http://ilk.uvt.nl/downloads/pub/papers/ilkXXXX.pdf}''} + https://languagemachines.github.io/timbl}''} -For information about commercial licenses for TiMBL 6.4, -contact {\tt Timbl@uvt.nl}, or send your request in writing to: +For information about commercial licenses for TiMBL 7.0, +contact {\tt lamasoftware@science.ru.nl}, or send your request in writing to: -Prof. dr.~Walter Daelemans\\ -CLiPS - Language Technology Group\\ -Dept. of Linguistics \\ -University of Antwerp\\ -Prinsstraat 13, L-203, B-2000 Antwerp \\ -Belgium +Prof. dr.~Antal van den Bosch\\ +Utrecht University\\ +Faculty of Humanities\\ +P.O. Box 80125\\ +3508 TC Utrecht\\ +the Netherlands \pagestyle{headings} \chapter{Installation} \vspace{-1cm} -You can get the TiMBL package as a gzipped tar archive from: +Before installing TiMBL from source, you should first check whether +your operating system's package manager already offers an up-to-date +package for it (TiMBL is available in, among others, Debian, Ubuntu and +Homebrew). If so, that is by far the easiest route. -{\tt http://ilk.uvt.nl/timbl} +The home of the TiMBL project is on GitHub: -Following the links from that page, you can download the file {\tt - timbl-latest.tar.gz}. This file contains the complete source code (C++) -for the TiMBL program, a few sample data sets, the license, and -documentation. The installation should be relatively straightforward -on most UNIX systems. +{\tt https://github.com/LanguageMachines/timbl} -To install the package on your computer, unzip the downloaded file ({\tt >} is the command line prompt): +and its documentation and further information can be found at: -{\tt > tar xfz timbl-latest.tar.gz} +{\tt https://languagemachines.github.io/timbl} -This will make a directory {\tt timbl-6.4} under your current -directory. (The numbering may be higher; the current guide refers to -version 6.4). +To build TiMBL from source, download the latest release tarball from +the releases page +(\url{https://github.com/LanguageMachines/timbl/releases}), or clone the +repository directly with {\tt git}. The source distribution contains the +complete source code (C++), a few sample data sets, the license, and +documentation. Building should be relatively straightforward on most +UNIX-like systems (Linux and macOS). + +To install from a release tarball, unzip the downloaded file ({\tt >} is the command line prompt): -Alternatively you can do: +{\tt > tar xfz timbl-7.0.tar.gz} -{\tt > gunzip timbl-6.4.tar.gz} +This will make a directory {\tt timbl-7.0} under your current +directory. (The numbering may be higher; the current guide refers to +version 7.0). + +Alternatively, to build the latest development version, clone the +repository: -and unpack the tar archive: +{\tt > git clone https://github.com/LanguageMachines/timbl.git} \\ +{\tt > cd timbl} \\ +{\tt > bash bootstrap.sh} -{\tt > tar xf timbl-6.4.tar} +TiMBL depends on a few other packages, most notably {\tt ticcutils} +(also available from the LanguageMachines GitHub organisation), +{\tt pkg-config}, {\tt libicu} and {\tt libxml2}. Install these through +your distribution's package manager before configuring; alternatively, +running {\tt ./build-deps.sh} will fetch and build the +LanguageMachines dependencies for you. -Go to the timbl-6.4 directory, and configure the package by typing +Go to the source directory, and configure the package by typing -{\tt > cd timbl-6.4} \\ {\tt > ./configure --prefix=} If you do not use the {\tt --prefix} option, TiMBL will try to install @@ -215,9 +231,9 @@ \chapter{Installation} It is not obligatory to install TiMBL, but if you plan to install TiMBL-based extensions such as -TimblServer\footnote{\url{http://ilk.uvt.nl/timbl}}, -Mbt\footnote{\url{http://ilk.uvt.nl/mbt}}, or -Frog\footnote{\url{http://ilk.uvt.nl/frog}}, or you want to +TimblServer\footnote{\url{https://github.com/LanguageMachines/timblserver}}, +Mbt\footnote{\url{https://languagemachines.github.io/mbt}}, or +Frog\footnote{\url{https://languagemachines.github.io/frog}}, or you want to build your own extensions using the TiMBL API, installing is the best choice. @@ -237,7 +253,7 @@ \chapter{Installation} tse} are created in the {\tt ./demos} subdirectory. Within the {\tt } directory a subdirectory is -also created: {\tt share/doc/timbl} where the TiMBL 6.4 documentation +also created: {\tt share/doc/timbl} where the TiMBL 7.0 documentation can be found, and which in turn contains a subdirectory {\tt examples} with example data files. Some of these data sets are used in the Quick Start Section~\ref{tutorial} of this document; other data and source @@ -269,16 +285,59 @@ \chapter{Installation} src} directory of the build. The demo files can be found in the {\tt demo} directory. -The email address for problems with the installation, bug reports, -comments and questions is {\tt Timbl@uvt.nl}. +Problems with the installation, bug reports, comments and questions +are welcome at our issue tracker, +\url{https://github.com/LanguageMachines/timbl/issues}. \chapter{Changes} \label{changes} This chapter gives a brief overview of the changes from all previously -released versions (1.0 up to 6.4) for users already familiar with the +released versions (1.0 up to 7.0) for users already familiar with the program. +\section{From version 6.4 to 7.0} + +Between version 6.4 and 7.0, TiMBL saw a long series of incremental +releases. Most of these focused on internal code quality, build-system +modernisation, and bug fixes; the changes most relevant to users are +summarised below. The {\tt NEWS} and {\tt ChangeLog} files in the +source repository give the complete per-release history. + +\begin{itemize} +\item With {\tt --prune}, an IGTree instance base can now be pruned + directly from an IB1/TRIBL2 instance base, instead of after a full + training: TiMBL reads an existing instance base ({\tt -i}), + optionally adds new training material ({\tt -f}), prunes the tree, + and writes the result to a new file ({\tt -I}). +\item With {\tt --limit }, classification can be restricted to the + {\tt } features with the highest weights; TiMBL automatically + restarts with an adapted {\tt -m} option that ignores the remaining + features. +\item The options {\tt -f} (training file) and {\tt -i} (instance + base) may now be used without {\tt -t}, that is, to build and store + an instance base without immediately testing. +\item A new {\tt Tabbed} input format was added to the {\tt -F} + option, in which fields are separated by tab characters, so that + spaces within field values are significant. +\item TiMBL now handles Unicode (UTF-8) input robustly: strings are + internally normalised to NFC, which makes the program reliable on + text in a wide range of scripts, including non-Latin ones. +\item The long options {\tt --version} and {\tt --help} are now + accepted alongside {\tt -V} and {\tt -h}. +\end{itemize} + +For developers using the TiMBL API, version 6.8 introduced a major +refactoring that modernises the code (Unicode strings are now the +default, and C-style arrays and casts were removed) and that breaks +both the API and the ABI; code written against earlier versions may +need to be adapted and recompiled. Building TiMBL now requires a +C++17 compiler. The dependencies on Boost and libtar have been +removed; TiMBL relies on {\tt ticcutils}, {\tt libicu} and {\tt + libxml2}. Since version 6.4.7 the source repository is hosted on +GitHub, and a {\tt Dockerfile} and a {\tt build-deps.sh} helper script +are provided. + \section{From version 6.3 to 6.4} \begin{itemize} @@ -314,14 +373,15 @@ \section{From version 6.2 to 6.3} \begin{itemize} \item All server-related functionality is removed from TiMBL. A new - TimblServer package is available wich provides the same interface as - Timbl up to version 6.3, but also adds some extra features, such as + TimblServer package is available which provides the same interface as + TiMBL up to version 6.3, but also adds some extra features, such as running multiple but separate experiments on one TCP port. See the TimblServer package for more details. -\item Starting with Timbl 6.3 we support installable packages for - Debian and Ubuntu (.deb), RedHat (.rpm) and MacOSX - (Fink)\footnote{\url{http://ilk.uvt.nl/timbl-packages}}. +\item Starting with TiMBL 6.3 we support installable packages for + Debian and Ubuntu (.deb), RedHat (.rpm) and + macOS\footnote{Up-to-date packaging information is available from + \url{https://languagemachines.github.io/timbl}}. \item Some bugs and inconsistencies have been fixed. @@ -927,11 +987,11 @@ \section{Using TiMBL} {\footnotesize \begin{verbatim} -TiMBL 6.4.2 (c) ILK 1998 - 2011. +TiMBL 7.0 (c) CLS/ILK/CLiPS 1998 - 2026. Tilburg Memory Based Learner -Induction of Linguistic Knowledge Research Group, Tilburg University +Centre for Language Studies, Radboud University Nijmegen CLiPS Computational Linguistics Group, University of Antwerp -Mon Apr 23 15:43:26 2012 +Tue Jun 23 12:00:00 2026 Examine datafile 'dimin.train' gave the following results: Number of Features: 12 @@ -2592,7 +2652,13 @@ \subsubsection{Linguistic and psycholinguistic modelling} \cite{VandenBosch+00b}, phonological bootstrapping \cite{Durieux+00}, the prediction of linking morphemes in Dutch \cite{Krott+01}, morphology \cite{Eddington00,Eddington03}, and the Dutch plural -inflection \cite{Keuleers+07}. \namecite{Vandekerckhove+13} use +inflection \cite{Keuleers+07}, including more recent work modelling the +production of variable plural forms in Dutch \cite{Zee+21}. +\namecite{VanCraenenbroeck+19} use $k$-nearest neighbor classification +in TiMBL to analyse syntactic microvariation in the word order of Dutch +verb clusters, and \namecite{VanCraenenbroeck+23} apply leave-one-out +$k$-nearest neighbor classification in TiMBL to study morphosyntactic +variation across some 260 Dutch dialects. \namecite{Vandekerckhove+13} use TiMBL to develop a language bigram model and use this to explain behavior of patients with a specific impairment that prohibits them to assess adjective orderings as normal or less felicitous. @@ -2606,9 +2672,10 @@ \subsubsection{Linguistic and psycholinguistic modelling} \subsubsection{Applications in syntax and semantics} At the {\bf syntactic} sentence level TiMBL has been applied to -Part-of-Speech tagging \cite{Daelemans+96b,Zavrel+99,Halteren+01}; +Part-of-Speech tagging \cite{Daelemans+96b,Zavrel+99,Halteren+01,Griebenouw+19}; PP-attachment \cite{Zavrel+97b}; subcategorization \cite{Buchholz98}; -phrase chunking \cite{Veenstra98,Sang+99}; shallow parsing of English +phrase chunking \cite{Veenstra98,Sang+99}; multi-level sequence +labeling \cite{Chen+19}; shallow parsing of English \cite{Daelemans+99a,Buchholz+99,Yeh00} and Arabic \cite{Azmi+10}; clause identification \cite{Orasan00,Sang01}; detecting the scope of negation markers and hedge cues \cite{Morante+08c,Morante+09c}; @@ -2644,6 +2711,8 @@ \subsubsection{Other applications} \cite{Buchholz+00,Hendrickx+03,DeMeulder+03,Sporleder+06b,Leveling+06,VandenBosch+13c}, information extraction \cite{Zavrel+00b,Zavrel+03,Ahn06}, event extraction \cite{Morante+09d}, text classification \cite{Spitters00}, +stance detection \cite{Shenoy+17}, the automatic classification of the +mood of songs from their lyrics \cite{VanZaanen+10}, question classification \cite{Garcia+06,Dridan+07}, spam filtering \cite{Androutsopoulos+00}, and authorship attribution \cite{Luyckx+08,Kestemont+09}. @@ -2664,7 +2733,12 @@ \subsubsection{Other applications} prediction and statistical language modeling are identified in \cite{VandenBosch05,VandenBosch06,Stehouwer+09b}. Next-word prediction with TiMBL has been specifically applied to {\bf word completion} -\cite{VandenBosch+08,VandenBosch11,Verberne+12,Stoop+14}. +\cite{VandenBosch+08,VandenBosch11,Verberne+12,Stoop+14}. More +recently, this memory-based approach to next-token prediction has been +scaled up with TiMBL into a transparent, CPU-only, and eco-friendly +alternative to neural {\bf large language models}, with next-token +prediction accuracy that scales log-linearly with the amount of +training data \cite{VandenBosch+25}. TiMBL has been shown to be a useful {\bf error detector} and corrector, such as in the context of error detection in textual @@ -2679,14 +2753,22 @@ \subsubsection{Other applications} in \cite{VandenBosch+07,Canisius+09,VandenBosch+09,VanGompel+09}; hybrids with statistical machine translation are presented in \cite{Stroppa+07,Haque+09,Haque+10}; sub-sentential paraphrasing using -pivot translations is described in \cite{Max09}. +pivot translations is described in \cite{Max09}. In related translation +tasks, \namecite{Tezcan+16} include TiMBL among the learners in their +machine-translation quality-estimation system for the WMT16 shared +task, and \namecite{Daems+17} train a TiMBL classifier to distinguish +human translations from post-edited machine translations +(``translationese'' versus ``post-editese''). Although most of the applications of TiMBL are in the natural language processing and computational linguistics areas, it is occasionally -used in other related domains as well. Examples are the classification -of newborns' cries \cite{Feier+14}, scaffolded learning by robots -\cite{Saunders+06}, or the detection of clinically important -micro-organisms through an electronic nose \cite{Moens+06}. +used in other domains as well. Examples are the classification of +newborns' cries \cite{Feier+14}, scaffolded learning by robots +\cite{Saunders+06}, the detection of clinically important +micro-organisms through an electronic nose \cite{Moens+06}, the +identification of cattle breeds from microsatellite {\sc dna} markers +\cite{Jaiswal+16}, and, through the TiMBL-based memory-based shallow +parser MBSP, the generation of visual art \cite{DeSmedt+11}. \subsubsection{Dissertations and special issue} @@ -2697,7 +2779,8 @@ \subsubsection{Dissertations and special issue} alignment, grapheme-to-phoneme conversion). TiMBL is also central in the Ph.D. theses of \namecite{Buchholz02}, \namecite{Lendvai04}, \namecite{Hendrickx05}, \namecite{Hoste05}, \namecite{Keuleers08}, -\namecite{Canisius09}, and \namecite{Vandekerckhove13}. +\namecite{Canisius09}, \namecite{Vandekerckhove13}, and +\namecite{Pijpops19}. In 1999 a special issue of the {\em Journal for Experimental and Theoretical Artificial Intelligence} (Vol.~11(3), edited by Walter @@ -2708,10 +2791,9 @@ \subsubsection{Dissertations and special issue} \ \\ -{\it All Tilburg/Antwerp papers referred to in this section, as well -as more recent papers, are available in electronic form from the {\sc -ILK} home page: {\tt http://ilk.uvt.nl} and the {\sc CLiPS} home page: \\ -{\tt http://www.clips.ua.ac.be/}.} +{\it Many of the papers referred to in this section are available in +electronic form from the {\sc CLiPS} home page: +\url{https://www.uantwerpen.be/en/research-groups/clips/}.} \chapter{Software usage and options} \label{reference} @@ -2726,11 +2808,11 @@ \section{Command line options} {\footnotesize \begin{verbatim} -TiMBL 6.4.2 (c) ILK 1998 - 2012. +TiMBL 7.0 (c) CLS/ILK/CLiPS 1998 - 2026. Tilburg Memory Based Learner -Induction of Linguistic Knowledge Research Group, Tilburg University +Centre for Language Studies, Radboud University Nijmegen CLiPS Computational Linguistics Group, University of Antwerp -Mon Apr 23 15:43:26 2012 +Tue Jun 23 12:00:00 2026 usage: timbl -f data-file {-t test-file} or see: timbl -h @@ -2953,12 +3035,20 @@ \subsection{Input options} \item {\tt -F } : Force TiMBL to interpret the training and test file as a specific data format. Possible values for this -parameter are: {\tt Compact, C4.5, ARFF, Columns, Sparse, Binary} -(case-insensitive). The default is that TiMBL guesses the format from -the contents of the first line of the data file. ARFF is not -automatically detected. See section~\ref{dataformats} for description -of the data formats and the guessing rules. The {\tt Compact} format -cannot be used with numeric features. +parameter are: {\tt Compact, C4.5, ARFF, Columns, Tabbed, Sparse, + Binary} (case-insensitive). The default is that TiMBL guesses the +format from the contents of the first line of the data file. ARFF is +not automatically detected. In the {\tt Tabbed} format, fields are +separated by single tab characters, so that spaces inside a +feature-value or category symbol are significant. See +section~\ref{dataformats} for description of the data formats and the +guessing rules. The {\tt Compact} format cannot be used with numeric +features. + +\item {\tt --limit } : Restrict classification to the {\tt } + features that have the highest weights. TiMBL automatically restarts + with an adapted {\tt -m} option that ignores the remaining + features. This option cannot be combined with cross-validation. \item {\tt -l } : Feature length. Only applicable with the Compact data format; {\tt } is the number of characters used for each @@ -2968,7 +3058,9 @@ \subsection{Input options} instead of processing a training file, read a previously saved (see {\tt -I} option) instance-base or {\sc IGTree} from the file {\tt treefile}. See section~\ref{treeformat} for the format of this - file. + file. Both {\tt -i} and {\tt -f} may be used without {\tt -t}, for + instance to build and save an instance base without classifying a + test set in the same run. \item {\tt --matrixin=} : Read value distance metrics (such as {\sc mvdm} or Jeffrey divergence matrices written to file with @@ -3013,6 +3105,12 @@ \subsection{Output options} overridden by {\tt -W}. See section~\ref{treeformat} for a description of the resulting file's format. +\item {\tt --prune} : Prune an {\sc IGTree} instance base directly from + an IB1/TRIBL2 instance base, instead of after a full training run. + TiMBL reads an existing instance base ({\tt -i}), optionally adds new + training material ({\tt -f}), prunes the resulting tree, and writes + it to the file given with {\tt -I} (which is therefore required). + \item {\tt --matrixout=} : Store calculated {\sc mvdm} or Jeffrey divergence distance metrics in file {\tt filename}. @@ -3200,7 +3298,7 @@ \subsection{Hidden options} weight thus becomes $\epsilon$. This modification ``diversifies'' the feature weights, and was introduced to enhance the effect of {\sc Dimbl}, the multi-CPU variant of TiMBL\footnote{For {\sc - Dimbl}, see \url{http://ilk.uvt.nl/dimbl}}. + Dimbl}, see \url{https://github.com/LanguageMachines/dimbl}}. \end{description} \section{File formats} diff --git a/docs/texfiles/ilk.bib b/docs/texfiles/ilk.bib index c91a718..36462b4 100755 --- a/docs/texfiles/ilk.bib +++ b/docs/texfiles/ilk.bib @@ -156,7 +156,7 @@ @inproceedings{Brousseau+95 Booktitle = {Proceedings of Eurospeech-1995}, Date-Added = {2015-06-06 12:36:39 +0000}, Date-Modified = {2015-06-06 12:37:47 +0000}, - Title = {French speech recognition in an automatic dictation system for translators: the transtalk project.}, + Title = {{F}rench speech recognition in an automatic dictation system for translators: the transtalk project.}, Year = {1995}} @inproceedings{Fougeron+01, @@ -184,7 +184,7 @@ @article{Pontes+10 Journal = {Speech Communication}, Number = {10}, Pages = {847--862}, - Title = {Predicting the phonetic realizations of word-final consonants in context--A challenge for French grapheme-to-phoneme converters}, + Title = {Predicting the phonetic realizations of word-final consonants in context--A challenge for {F}rench grapheme-to-phoneme converters}, Volume = {52}, Year = {2010}} @@ -195,7 +195,7 @@ @inproceedings{Karsdorp+15c Date-Modified = {2015-05-31 13:03:48 +0000}, Editor = {M. A. Finlayson and B. Miller and A. Lieto and R. Ronfard}, Pages = {89--107}, - Title = {The love equation: Computational modeling of romantic relationships in French classical drama}, + Title = {The love equation: Computational modeling of romantic relationships in {F}rench classical drama}, Year = {2015}} @inproceedings{Karsdorp+15b, @@ -270,7 +270,7 @@ @article{VandenBosch14 Date-Modified = {2015-05-02 19:25:28 +0000}, Journal = {Machine Translation}, Pages = {57--60}, - Title = {Book review: Peter Spyns and Jan Odijk (eds): Essential speech and language technology for Dutch: results by the STEVIN programme}, + Title = {Book review: Peter Spyns and Jan Odijk (eds): Essential speech and language technology for {D}utch: results by the STEVIN programme}, Volume = {28}, Year = {2014}} @@ -297,7 +297,7 @@ @incollection{VanGompel+14c Date-Modified = {2015-05-02 13:01:49 +0000}, Pages = {287--296}, Publisher = {Fryske Akademy}, - Title = {Oersetter: Frisian-Dutch statistical machine translation}, + Title = {Oersetter: {F}risian-{D}utch statistical machine translation}, Year = {2014}} @inproceedings{VanGompel+14b, @@ -338,7 +338,7 @@ @article{Tellings+14 Date-Modified = {2015-05-02 12:55:20 +0000}, Journal = {Computational Linguistics in the Netherlands Journal}, Pages = {191--208}, - Title = {BasiLex: An 11.5 million words corpus of Dutch texts written for children}, + Title = {BasiLex: An 11.5 million words corpus of {D}utch texts written for children}, Volume = {4}, Year = {2014}} @@ -348,7 +348,7 @@ @article{PanderMaat+14 Date-Modified = {2015-05-02 12:54:38 +0000}, Journal = {Computational Linguistics in the Netherlands Journal}, Pages = {53--74}, - Title = {T-Scan: A new tool for analyzing Dutch text}, + Title = {T-Scan: A new tool for analyzing {D}utch text}, Volume = {4}, Year = {2014}} @@ -502,7 +502,7 @@ @incollection{Gaillat+14 Editor = {L. Vandelanotte and K. Davidse and C. Gentens and D. Kimps}, Pages = {309--324}, Publisher = {Rodopi}, - Title = {Automated classification of unexpected uses of {\em this} and {\em that} in a learner corpus of English}, + Title = {Automated classification of unexpected uses of {\em this} and {\em that} in a learner corpus of {E}nglish}, Year = {2014}} @inproceedings{Silva+14, @@ -1039,7 +1039,7 @@ @url{Davies13 Date-Added = {2013-12-08 21:10:19 +0000}, Date-Modified = {2013-12-08 23:16:59 +0000}, Lastchecked = {December 8, 2013}, - Title = {{Corpus of Global Web-Based English}: 1.9 billion words from speakers in 20 countries}, + Title = {{Corpus of Global Web-Based {E}nglish}: 1.9 billion words from speakers in 20 countries}, Urldate = {http://corpus2.byu.edu/glowbe/}, Year = {2013--}} @@ -1050,7 +1050,7 @@ @article{Campbell+01 Journal = {Applied Psycholinguistics}, Number = {2}, Pages = {253--267}, - Title = {The acquisition of English dative constructions}, + Title = {The acquisition of {E}nglish dative constructions}, Volume = {22}, Year = {2001}} @@ -1126,7 +1126,7 @@ @inproceedings{Strik+02 Date-Added = {2013-11-04 11:22:52 +0000}, Date-Modified = {2013-12-15 13:11:31 +0000}, Pages = {1549--1552}, - Title = {Dutch {HLT} resources: from {BLARK} to priority lists}, + Title = {{D}utch {HLT} resources: from {BLARK} to priority lists}, Year = {2002}} @inproceedings{Krauwer03, @@ -1146,7 +1146,7 @@ @article{Bouma+01 Number = {1}, Pages = {45--59}, Publisher = {Rodopi}, - Title = {Alpino: Wide-coverage computational analysis of Dutch}, + Title = {Alpino: Wide-coverage computational analysis of {D}utch}, Volume = {37}, Year = {2001}} @@ -1212,7 +1212,7 @@ @article{Grondelaers+09 Number = {2}, Pages = {153--160}, Publisher = {Elsevier}, - Title = {Introducing a new entity into discourse: Comprehension and production evidence for the status of Dutch {\it er} ``there'' as a higher-level expectancy monitor}, + Title = {Introducing a new entity into discourse: Comprehension and production evidence for the status of {D}utch {\it er} ``there'' as a higher-level expectancy monitor}, Volume = {130}, Year = {2009}} @@ -1223,7 +1223,7 @@ @phdthesis{Theijssen12 Keywords = {dative alternation}, Month = {June}, School = {Radboud University Nijmegen}, - Title = {Making choices: Modelling the English dative alternation}, + Title = {Making choices: Modelling the {E}nglish dative alternation}, Year = {2012}} @incollection{Grondelaers+08, @@ -1342,7 +1342,7 @@ @proceedings{Eickhoff+13 Issn = {1613-0073}, Number = 986, Series = {CEUR Workshop Proceedings}, - Title = {Proceedings of the 13th Dutch-Belgian Workshop on Information Retrieval (DIR)}, + Title = {Proceedings of the 13th {D}utch-Belgian Workshop on Information Retrieval (DIR)}, Url = {http://ceur-ws.org/Vol-986/}, Venue = {Delft, The Netherlands}, Year = 2013, @@ -1906,7 +1906,7 @@ @book{Odijk12 Note = {Available online at \url{http://www.meta-net.eu/whitepapers}}, Publisher = {Springer}, Series = {META-NET White Paper Series}, - Title = {{Het Nederlands in het Digitale Tijdperk -- The Dutch Language in the Digital Age}}, + Title = {{Het Nederlands in het Digitale Tijdperk -- The {D}utch Language in the Digital Age}}, Year = {2012}} @article{Bannard+08, @@ -1983,7 +1983,7 @@ @incollection{Mos+12 Keywords = {vici, cls, lst, language modeling, human language processing, perplexity}, Pages = {207--240}, Publisher = {Mouton De Gruyter}, - Title = {The predictive value of word-level perplexity in human sentence processing: A case study on fixed adjective--preposition constructions in Dutch}, + Title = {The predictive value of word-level perplexity in human sentence processing: A case study on fixed adjective--preposition constructions in {D}utch}, Volume = {1}, Year = {2012}} @@ -3116,7 +3116,7 @@ @inproceedings{Oostdijk00 Date-Added = {2012-03-27 18:43:06 +0000}, Date-Modified = {2012-03-27 18:43:33 +0000}, Pages = {887--894}, - Title = {{The spoken Dutch corpus: overview and first evaluation}}, + Title = {{The spoken {D}utch corpus: overview and first evaluation}}, Volume = {2}, Year = {2000}} @@ -3187,7 +3187,7 @@ @inproceedings{Ordelman+01 Booktitle = {Proceedings of Eurospeech 2001}, Date-Added = {2011-10-17 21:26:52 +0000}, Date-Modified = {2011-10-17 21:27:57 +0000}, - Title = {Lexicon optimization for Dutch speech recognition in spoken document retrieval}, + Title = {Lexicon optimization for {D}utch speech recognition in spoken document retrieval}, Year = {2001}} @incollection{Daelemans+10b, @@ -3648,7 +3648,7 @@ @phdthesis{Palazuelos01 Date-Modified = {2011-03-27 22:32:27 +0200}, Keywords = {word completion, word prediction, augmentative technology}, School = {Universidad Politechnica de Madrid}, - Title = {Contribution to Word Prediction in Spanish and its Integration in Technical Aids for People With Physical Disabilities}, + Title = {Contribution to Word Prediction in {S}panish and its Integration in Technical Aids for People With Physical Disabilities}, Year = {2001}} @inproceedings{Shein+01, @@ -4081,7 +4081,7 @@ @article{Plag+07 Number = {2}, Pages = {199--232}, Publisher = {Citeseer}, - Title = {{Testing hypotheses about compound stress assignment in English: a corpus-based investigation}}, + Title = {{Testing hypotheses about compound stress assignment in {E}nglish: a corpus-based investigation}}, Volume = {3}, Year = {2007}} @@ -4479,7 +4479,7 @@ @book{Mitton96 Date-Added = {2010-11-01 21:51:15 +0100}, Date-Modified = {2011-06-19 23:01:09 +0200}, Publisher = {Longman}, - Title = {English Spelling and the Computer}, + Title = {{E}nglish Spelling and the Computer}, Year = {1996}} @inproceedings{VandenHoven+10, @@ -4954,7 +4954,7 @@ @inproceedings{Adamson+96 Author = {M. Adamson and R. Damper}, Booktitle = {Proceedings of the International Conference on Spoken Language Processing, ICSLP-96}, Pages = {1704--1707}, - Title = {A recurrent network that learns to pronounce English text}, + Title = {A recurrent network that learns to pronounce {E}nglish text}, Volume = 4, Year = 1996} @@ -5138,7 +5138,7 @@ @inproceedings{Ait-Mokhtar+97b @book{Alcalay90, Author = {R. Alcalay}, Publisher = {Massada}, - Title = {The Complete Hebrew-English Dictionary}, + Title = {The Complete {H}ebrew-{E}nglish Dictionary}, Year = 1990} @inproceedings{Alegre+99, @@ -5724,7 +5724,7 @@ @book{Bauer83 Address = {Cambridge, UK}, Author = {L. Bauer}, Publisher = CUP, - Title = {English word-formation}, + Title = {{E}nglish word-formation}, Year = 1983} @book{Bauer88, @@ -5746,7 +5746,7 @@ @inproceedings{Beale88 Booktitle = ANLP, Date-Modified = {2010-09-18 14:36:44 +0200}, Keywords = {part-of-speech tagging}, - Title = {Lexicon and grammar in probabilistic tagging of written English}, + Title = {Lexicon and grammar in probabilistic tagging of written {E}nglish}, Year = 1988} @misc{Beckwith+??, @@ -5914,7 +5914,7 @@ @inproceedings{Bick06 Author = {E. Bick}, Booktitle = {A Man of Measure: Festschrift in Honour of Fred Karlsson on his 60th Birthday; a special supplement to SKY Journal of Linguistics}, Pages = {387--396}, - Title = {A Constraint Grammar Based Spellchecker for Danish with a Special Focus on Dyslexics}, + Title = {A Constraint Grammar Based Spellchecker for {D}anish with a Special Focus on Dyslexics}, Year = {2006}} @phdthesis{Biemann07, @@ -5936,7 +5936,7 @@ @article{Biewer+85 Date-Modified = {2011-01-29 16:38:29 +0100}, Journal = CL, Number = {2--3}, - Title = {{ASCOF} -- A modular multilevel system for French-German translation}, + Title = {{ASCOF} -- A modular multilevel system for {F}rench-{G}erman translation}, Volume = 11, Year = 1985} @@ -6225,7 +6225,7 @@ @phdthesis{Bogers09 @inproceedings{Boguraev+87, Author = {B. Boguraev and E. Briscoe and J. Carroll and D. Carter and C. Grover}, Booktitle = ACL87, - Title = {{The derivation of a grammatically-indexed lexicon from the Longman Dictionary of Contemporary English}}, + Title = {{The derivation of a grammatically-indexed lexicon from the Longman Dictionary of Contemporary {E}nglish}}, Year = 1987} @article{Bohanec+90, @@ -6433,7 +6433,7 @@ @book{Brent91 Address = {Cambridge MA}, Author = {Michael R. Brent}, Publisher = MIT, - Title = {Automatic acquisition of subcategorization frames from unrestricted English}, + Title = {Automatic acquisition of subcategorization frames from unrestricted {E}nglish}, Year = 1991} @inproceedings{Brent91b, @@ -6787,7 +6787,7 @@ @book{Brunak+90 @article{Brysbaert+96, Author = {M. Brysbaert and D.C. Mitchell}, Journal = {Quarterly Journal of Experimental Psychology}, - Title = {Modifier attachment in sentence parsing: Evidence from Dutch}, + Title = {Modifier attachment in sentence parsing: Evidence from {D}utch}, Volume = {49A}, Year = 1996} @@ -6932,7 +6932,7 @@ @inproceedings{Busser98 Keywords = {ilk, grapheme-phoneme conversion, speech synthesis}, Pages = {3--8}, Publisher = {Masaryk University}, - Title = {{TreeTalk-D}: A Machine Learning approach to Dutch word pronunciation}, + Title = {{TreeTalk-D}: A Machine Learning approach to {D}utch word pronunciation}, Year = {1998}, Bdsk-Url-1 = {http://ilk.uvt.nl/downloads/pub/papers/TSD98.ps.gz}} @@ -8168,7 +8168,7 @@ @article{Cossu+88 Author = {G. Cossu and D. Shankweiler and I. Y. Liberman and L. Katz and G. Tola}, Journal = {Applied Psycholinguistics}, Pages = {1--16}, - Title = {Awareness of phonological segments and reading ability in Italian children}, + Title = {Awareness of phonological segments and reading ability in {I}talian children}, Volume = 9, Year = 1988} @@ -8658,7 +8658,7 @@ @article{Daelemans+97b Keywords = {ilk, diminutive inflection, Dutch}, Number = {1--2}, Pages = {57--75}, - Title = {Data mining as a method for linguistic analysis: Dutch diminutives}, + Title = {Data mining as a method for linguistic analysis: {D}utch diminutives}, Volume = {XXXI}, Year = 1997} @@ -9187,7 +9187,7 @@ @inproceedings{Daya+04 Date-Added = {2009-11-15 00:19:26 +0100}, Date-Modified = {2009-11-15 00:19:35 +0100}, Pages = {168--178}, - Title = {Learning Hebrew Roots: Machine Learning with Linguistic Constraints}, + Title = {Learning {H}ebrew Roots: Machine Learning with Linguistic Constraints}, Year = {2004}} @article{Daya+08, @@ -9197,7 +9197,7 @@ @article{Daya+08 Journal = {Computational Linguistics}, Number = {3}, Pages = {429--448}, - Title = {Learning Hebrew Roots: Machine Learning with Linguistic Constraints}, + Title = {Learning {H}ebrew Roots: Machine Learning with Linguistic Constraints}, Volume = {34}, Year = {2008}} @@ -9449,7 +9449,7 @@ @inproceedings{Diab+04 Author = {M. Diab and K. Hacioglu and D. Jurafsky}, Booktitle = {Proceedings of HLT-NAACL 2004}, Pages = {149--152}, - Title = {Automatic Tagging of Arabic Text: From raw text to Base Phrase Chunks}, + Title = {Automatic Tagging of {A}rabic Text: From raw text to Base Phrase Chunks}, Year = 2004} @inproceedings{Dietterich+91, @@ -9611,7 +9611,7 @@ @inproceedings{Dridan+07 Date-Modified = {2009-11-14 18:51:47 +0100}, Keywords = {question answering}, Pages = {333--341}, - Title = {What to classify and how: Experiments in question classification for Japanese}, + Title = {What to classify and how: Experiments in question classification for {J}apanese}, Year = 2007} @article{Dronkers96, @@ -9697,7 +9697,7 @@ @article{Earley70 @inproceedings{Eckle+96, Author = {Judith Eckle and Ulrich Heid}, Booktitle = {Proceedings of the 4th International Conference on Computational Lexicography, COMPLEX '96, Budapest, Hungary}, - Title = {Extracting raw material for a German subcategorization lexicon from newspaper text}, + Title = {Extracting raw material for a {G}erman subcategorization lexicon from newspaper text}, Year = 1996} @unpublished{Eckle+98, @@ -9709,7 +9709,7 @@ @unpublished{Eckle+98 @misc{Eckle+??, Author = {Judith Eckle and Ulrich Heid}, - Title = {Extracting raw material for a German subcategorization lexicon from newspaper text}} + Title = {Extracting raw material for a {G}erman subcategorization lexicon from newspaper text}} @article{Eddington00, Author = {David Eddington}, @@ -9758,7 +9758,7 @@ @inproceedings{Egedi+94 Booktitle = {Proceedings of the International Workshop on Sharable Natural Language Resources, Nara, Japan}, Month = {August}, Pages = {123--130}, - Title = {A Freely Avaiable Syntactic Lexicon for English}, + Title = {A Freely Avaiable Syntactic Lexicon for {E}nglish}, Year = 1994} @inproceedings{Eijk93, @@ -10046,7 +10046,7 @@ @misc{Fellbaum+93 @misc{Fellbaum93, Author = {C. Fellbaum}, Howpublished = {available from: {\tt\small http://www.cogsci.princeton.edu/\ { }wn/}}, - Title = {English Verbs as a Semantic Net}, + Title = {{E}nglish Verbs as a Semantic Net}, Year = 1993} @book{Fellbaum98, @@ -10372,7 +10372,7 @@ @book{Francis+82 Author = {W. Francis and H. Ku\v{c}era}, Date-Modified = {2011-06-21 18:11:30 +0200}, Publisher = {Houghton Mifflin Company}, - Title = {Frequency Analysis of English Usage}, + Title = {Frequency Analysis of {E}nglish Usage}, Year = 1982} @incollection{Franz96, @@ -10621,7 +10621,7 @@ @inproceedings{Fung95b Author = {Pascale Fung}, Booktitle = {Proceedings of the Third Annual Workshop on Very Large Corpora}, Pages = {173--183}, - Title = {Compiling Bilingual Lexicon Entries from a Non-Parallel English-Chinese Corpus}, + Title = {Compiling Bilingual Lexicon Entries from a Non-Parallel {E}nglish-{C}hinese Corpus}, Year = 1995} @inproceedings{Fung96, @@ -10785,7 +10785,7 @@ @inproceedings{Garcia+06 Date-Modified = {2011-01-29 16:41:41 +0100}, Keywords = {question classification}, Pages = {39--44}, - Title = {{BRUJA}: Question classification for Spanish}, + Title = {{BRUJA}: Question classification for {S}panish}, Year = 2006} @book{Gardner87, @@ -11623,7 +11623,7 @@ @book{Halle+71 Address = {New York, NY}, Author = {M. Halle and S. J. Keyser}, Publisher = {Harper and Row}, - Title = {English stress: its form, its growth, and its role in verse}, + Title = {{E}nglish stress: its form, its growth, and its role in verse}, Year = 1971} @incollection{Halle78, @@ -11744,7 +11744,7 @@ @article{Han+06 Journal = {Natural Language Engineering}, Number = {02}, Pages = {115-129}, - Title = {Detecting errors in English article usage by non-native speakers}, + Title = {Detecting errors in {E}nglish article usage by non-native speakers}, Url = {http://journals.cambridge.org/action/displayAbstract?fromPage=online&aid=439987&fulltextType=RA&fileId=S1351324906004190}, Volume = {12}, Year = {2006}, @@ -12016,7 +12016,7 @@ @inproceedings{Hendrickx+02 Date-Modified = {2010-09-18 14:23:11 +0200}, Keywords = {ilk, wsd, word sense disambiguation, memory-based learning, memory-based language processing, Dutch, vi}, Pages = {61--65}, - Title = {Dutch word sense disambiguation: Optimizing the localness of context}, + Title = {{D}utch word sense disambiguation: Optimizing the localness of context}, Year = 2002} @inproceedings{Hendrickx+03, @@ -12382,7 +12382,7 @@ @book{Hornby89 Author = {A. S. Hornby}, Edition = 4, Publisher = {Oxford University Press}, - Title = {Oxford Advanced Learner's Dictionary of Current English}, + Title = {Oxford Advanced Learner's Dictionary of Current {E}nglish}, Year = 1989} @techreport{Hornik+89, @@ -12397,7 +12397,7 @@ @inproceedings{Hoste+01 Booktitle = {Proceedings of Senseval-2}, Date-Modified = {2009-09-06 20:38:18 +0200}, Keywords = {wsd, word sense disambiguation, feature selection}, - Title = {Classifier Optimization and Combination in the English All Words Task}, + Title = {Classifier Optimization and Combination in the {E}nglish All Words Task}, Year = 2001} @article{Hoste+02, @@ -12421,7 +12421,7 @@ @inproceedings{Hoste+08 Editor = {C. Johansson}, Keywords = {ilk, co-reference resolution, Dutch, vici}, Pages = {51--75}, - Title = {A modular approach to learning Dutch co-reference}, + Title = {A modular approach to learning {D}utch co-reference}, Year = {2008}, Bdsk-Url-1 = {http://ilk.uvt.nl/downloads/pub/papers/war.pdf}} @@ -12791,7 +12791,7 @@ @book{Jelinek98 @techreport{Jensen86, Author = {K. Jensen}, Institution = {IBM T. J. Watson Research Center}, - Title = {PEG 1986: A broad-coverage computational syntax of English}, + Title = {PEG 1986: A broad-coverage computational syntax of {E}nglish}, Year = 1986} @article{Jensen87, @@ -12948,7 +12948,7 @@ @book{Jones96 @misc{Jones??, Author = {Doug Jones}, - Title = {Predicting Semantics from Syntactic Cues - An Evaluation of {Levin's English} Verb Classes and Alternations}} + Title = {Predicting Semantics from Syntactic Cues - An Evaluation of {Levin's {E}nglish} Verb Classes and Alternations}} @techreport{Jordan+93, Author = {M. I. Jordan and R. A. Jacobs}, @@ -13254,7 +13254,7 @@ @article{Keuleers+07 Journal = {Cognitive Psychology}, Number = 4, Pages = {283--318}, - Title = {Dutch plural inflection: The exception that proves the analogy}, + Title = {{D}utch plural inflection: The exception that proves the analogy}, Volume = 54, Year = 2007} @@ -13300,7 +13300,7 @@ @inproceedings{Kilgarriff+00 Date-Modified = {2009-09-06 20:39:17 +0200}, Keywords = {senseval, wsd, word sense disambiguation}, Pages = {1239--1243}, - Title = {English SENSEVAL: Report and Results}, + Title = {{E}nglish SENSEVAL: Report and Results}, Year = 2000} @book{Kilgarriff00, @@ -13320,7 +13320,7 @@ @inproceedings{Kilgarriff01 Keywords = {word sense disambiguation, lexical semantics}, Pages = {17-20}, Source = {Iris,web}, - Title = {English lexical sample task description}, + Title = {{E}nglish lexical sample task description}, Year = 2001} @inproceedings{Kim+06, @@ -13328,7 +13328,7 @@ @inproceedings{Kim+06 Author = {S.N. Kim and T. Baldwin}, Booktitle = {Proceedings of the Third ACL SIGSEM Workshop on Prepositions}, Pages = {65--72}, - Title = {Automatic identification of English verb particle constructions using linguistic features}, + Title = {Automatic identification of {E}nglish verb particle constructions using linguistic features}, Year = 2006} @inproceedings{Kim+06b, @@ -13631,7 +13631,7 @@ @article{Kokkinakis00 Journal = {Nordic Journal of Linguistics}, Number = 2, Pages = {191--213}, - Title = {{PP}-Attachment Disambiguation for Swedish: Combining Unsupervised and Supervised Training Data}, + Title = {{PP}-Attachment Disambiguation for {S}wedish: Combining Unsupervised and Supervised Training Data}, Volume = 23, Year = 2000} @@ -14416,21 +14416,21 @@ @book{Levin89 Address = {Evanston}, Author = {B. Levin}, Publisher = {Northwestern University}, - Title = {Towards a Lexical Organization of English Verbs}, + Title = {Towards a Lexical Organization of {E}nglish Verbs}, Year = 1989} @book{Levin93, Address = {Chicago}, Author = {B. Levin}, Publisher = {Chicago University Press}, - Title = {Towards a Lexical Organization of English Verbs}, + Title = {Towards a Lexical Organization of {E}nglish Verbs}, Year = 1993} @book{Levin93b, Address = {Chicago IL}, Author = {B. Levin}, Publisher = {University of Chicago Press}, - Title = {English Verb Classe and Alternations: A Preliminary Investigation}, + Title = {{E}nglish Verb Classe and Alternations: A Preliminary Investigation}, Year = 1993} @inproceedings{Levy+91, @@ -14508,7 +14508,7 @@ @inproceedings{Li+10 Month = {July}, Pages = {1108--1117}, Publisher = {Association for Computational Linguistics}, - Title = {Joint Syntactic and Semantic Parsing of Chinese}, + Title = {Joint Syntactic and Semantic Parsing of {C}hinese}, Year = {2010}} @inproceedings{Liang+06, @@ -14737,7 +14737,7 @@ @inproceedings{Maamouri+04 Address = {Geneva, Switzerland}, Author = {Mohamed Maamouri and Ann Bies}, Booktitle = {Proceedings of the Workshop on Computational Approaches to Arabic Script-based Languages, COLING 2004}, - Title = {Developing an Arabic Treebank: Methods, Guidelines, Procedures, and Tools}, + Title = {Developing an {A}rabic Treebank: Methods, Guidelines, Procedures, and Tools}, Year = 2004} @inproceedings{Maarek89, @@ -14994,7 +14994,7 @@ @article{Marcus+95 Author = {G.F. Marcus and U. Brinkmann and H. Clahsen and R. Wiese and S. Pinker}, Journal = {Cognitive Psychology}, Pages = {189--256}, - Title = {German inflection: The exception that proves the rule.}, + Title = {{G}erman inflection: The exception that proves the rule.}, Volume = 29, Year = 1995} @@ -15022,7 +15022,7 @@ @inproceedings{Marques+96 Booktitle = {Proceedings of the Fifth International Conference on The Cognitive Science of {NLP}, {CSNLP}, Dublin City University}, Date-Modified = {2009-11-14 17:36:54 +0100}, Keywords = {part-of-speech tagging, Portuguese}, - Title = {Using Neural Nets for Portuguese Part-of-Speech Tagging}, + Title = {Using Neural Nets for {P}ortuguese Part-of-Speech Tagging}, Year = 1996} @inproceedings{Marquez+97, @@ -15083,7 +15083,7 @@ @inproceedings{Marsi+05 Booktitle = {Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages}, Date-Modified = {2010-09-14 13:06:59 +0200}, Keywords = {ilk, part-of-speech tagging, morphological analysis, memory-based learning, Arabic, vi}, - Title = {Memory-based morphological analysis generation and part-of-speech tagging of Arabic}, + Title = {Memory-based morphological analysis generation and part-of-speech tagging of {A}rabic}, Year = 2006} @article{Marslen-Wilson75, @@ -15585,7 +15585,7 @@ @article{Minnen+01 Journal = JNLE, Number = 3, Pages = {207--223}, - Title = {Applied morphological processing of English}, + Title = {Applied morphological processing of {E}nglish}, Volume = 7, Year = 2001} @@ -15803,7 +15803,7 @@ @inproceedings{Morante+07 Date-Modified = {2010-09-14 13:06:31 +0200}, Keywords = {ilk, semantic role labeling, Catalan, Spanish, vici}, Pages = {388--394}, - Title = {Memory-based semantic role labelling of Catalan and Spanish}, + Title = {Memory-based semantic role labelling of {C}atalan and {S}panish}, Year = {2007}, Bdsk-Url-1 = {http://ilk.uvt.nl/downloads/pub/papers/srl_ranlp_def.pdf}} @@ -15827,7 +15827,7 @@ @inproceedings{Morante+08 Date-Modified = {2010-09-14 22:16:17 +0200}, Keywords = {clips, semantic role labeling}, Pages = {208-212}, - Title = {A Combined Memory-Based Semantic Role Labeler of English}, + Title = {A Combined Memory-Based Semantic Role Labeler of {E}nglish}, Year = {2008}} @article{Morante+08b, @@ -15838,7 +15838,7 @@ @article{Morante+08b Keywords = {dependency parsing, Spanish}, Number = {40}, Pages = {59--66}, - Title = {Experiments with an ensemble of Spanish dependency parsers}, + Title = {Experiments with an ensemble of {S}panish dependency parsers}, Year = {2008}} @inproceedings{Morante+08c, @@ -16053,7 +16053,7 @@ @inproceedings{Nakisa+96 Booktitle = {Proceedings of the 18th Annual Conference of the Cognitive Science Society}, Editor = {Garrison W. Cottrell}, Pages = {177--182}, - Title = {Where Defaults Don't Help: the Case of the German Plural System}, + Title = {Where Defaults Don't Help: the Case of the {G}erman Plural System}, Year = 1996} @inproceedings{Nastase+06, @@ -16068,7 +16068,7 @@ @inproceedings{Nagao+94 Booktitle = {COLING-94}, Date-Modified = {2011-06-19 23:01:27 +0200}, Pages = {611--615}, - Title = {A New Method of N-gram Statistics for Large Number of n and Automatic Extraction of Words and Phrases from Large Text Data of Japanese}, + Title = {A New Method of N-gram Statistics for Large Number of n and Automatic Extraction of Words and Phrases from Large Text Data of {J}apanese}, Year = {1994}} @article{Navarro+97, @@ -16455,7 +16455,7 @@ @inproceedings{Oostdijk+02 Date-Modified = {2012-11-28 22:28:07 +0000}, Editor = {M. {Gonz\'{a}lez Rodriguez} and C. {Paz Su\'{a}rez Araujo}}, Pages = {340--347}, - Title = {Experiences from the {Spoken Dutch Corpus} Project}, + Title = {Experiences from the {Spoken {D}utch Corpus} Project}, Year = 2002} @inproceedings{Oostdijk+08, @@ -16482,7 +16482,7 @@ @inproceedings{Orasan00 Address = {Monastir, Tunisia}, Author = {C. Or\u{a}san}, Booktitle = {Proceedings of ACIDCA '2000}, - Title = {A hybrid method for clause splitting in unrestricted English texts}, + Title = {A hybrid method for clause splitting in unrestricted {E}nglish texts}, Year = 2000} @inproceedings{Osborne00, @@ -16625,7 +16625,7 @@ @article{Palmer+09 Journal = {{Natural Language Engineering}}, Number = {1}, Pages = {143--172}, - Title = {{Adding semantic roles to the Chinese Treebank}}, + Title = {{Adding semantic roles to the {C}hinese Treebank}}, Volume = {15}, Year = {2009}} @@ -16744,7 +16744,7 @@ @inproceedings{Pereira+93 Author = {F. Pereira and N. Tishby and L. Lee}, Booktitle = {Proc. of the 30th Annual Meeting of the ACL}, Pages = {183--190}, - Title = {Distributional Clustering of English Words}, + Title = {Distributional Clustering of {E}nglish Words}, Year = 1993} @inproceedings{Pereira92, @@ -17318,7 +17318,7 @@ @book{Quirk+85 Address = {London}, Author = {R. Quirk and S. Greenbaum and G. Leech and J. Svartvik}, Publisher = {Longman}, - Title = {A comprehensive grammar of the English language}, + Title = {A comprehensive grammar of the {E}nglish language}, Year = 1985} @inproceedings{Raaijmakers00, @@ -18039,7 +18039,7 @@ @inproceedings{Sagae+07 @book{Sager81, Author = {N. Sager}, Publisher = {Addison-Wesley}, - Title = {Natural language information processing: A computer grammar of English and its applications}, + Title = {Natural language information processing: A computer grammar of {E}nglish and its applications}, Year = 1981} @inproceedings{Salganicoff93, @@ -18169,7 +18169,7 @@ @article{Sang+03b Journal = {Proceedings of CLIN}, Keywords = {clips, subtitling}, Pages = {109--123}, - Title = {Reduction of Dutch Sentences for Automatic Subtitling}, + Title = {Reduction of {D}utch Sentences for Automatic Subtitling}, Year = {2003}} @inproceedings{Sang+05, @@ -18434,7 +18434,7 @@ @article{Schneider01 Date-Modified = {2013-08-07 09:25:44 +0000}, Journal = {Language and Computers}, Pages = {199-211(13)}, - Title = {Computer assisted spelling normalization of 18th century English}, + Title = {Computer assisted spelling normalization of 18th century {E}nglish}, Volume = {36}, Year = {20 November 2001}} @@ -18978,7 +18978,7 @@ @techreport{Sleator+91 Address = {{Pittsburgh}}, Author = {D. Sleator and D. Temperley}, Institution = {CMU}, - Title = {Parsing English with a Link Grammar}, + Title = {Parsing {E}nglish with a Link Grammar}, Year = 1991} @inproceedings{Smadja+90, @@ -19089,7 +19089,7 @@ @book{Soudi+07 Editor = {A. Soudi and A. {Van den Bosch} and G. Neumann}, Keywords = {ilk, Arabic, morphological analysis, vici}, Publisher = {Springer Verlag}, - Title = {Arabic computational morphology: Knowledge-based and empirical methods}, + Title = {{A}rabic computational morphology: Knowledge-based and empirical methods}, Year = {2007}, Bdsk-Url-1 = {http://www.springer.com/east/home/linguistics/computational+linguistics?SGWID=5-40374-22-173729328-0}} @@ -19098,7 +19098,7 @@ @phdthesis{Soudi02 Date-Modified = {2009-11-14 18:55:25 +0100}, Keywords = {Arabic, morphological analysis}, School = {Mohamed V University (Morocco) and Carnegie Mellon University (USA)}, - Title = {A Computational Lexeme-based Treatment of Arabic Morphology}, + Title = {A Computational Lexeme-based Treatment of {A}rabic Morphology}, Year = 2002} @book{Sowa84, @@ -19351,7 +19351,7 @@ @inproceedings{Stevens+07 Editor = {P. Dirix and I. Schuurman and V. Vandeghinste and and F. {Van Eynde}}, Keywords = {ilk, semantic role labeling, Dutch, vici}, Pages = {99--114}, - Title = {A pilot study for semantic role labeling in a Dutch corpus}, + Title = {A pilot study for semantic role labeling in a {D}utch corpus}, Year = {2007}, Bdsk-Url-1 = {http://ilk.uvt.nl/downloads/pub/papers/stevensetal-clin17.pdf}} @@ -19559,7 +19559,7 @@ @inproceedings{Surdeanu+08b Pages = {206--218}, Publisher = {Springer Verlag}, Series = {Lecture Notes in Computer Science}, - Title = {Analysis of joint inference strategies for the semantic role labeling of Spanish and Catalan}, + Title = {Analysis of joint inference strategies for the semantic role labeling of {S}panish and {C}atalan}, Volume = {4919}, Year = {2008}, Bdsk-Url-1 = {http://ilk.uvt.nl/downloads/pub/papers/surdeanuetal-cicling08.pdf}} @@ -19782,7 +19782,7 @@ @inproceedings{Taule+08 Booktitle = {Proceedings of the {6th International Conference on Language Resources and Evaluation (LREC-2008)}}, Date-Added = {2009-12-26 20:57:57 +0100}, Date-Modified = {2011-07-02 22:18:13 +0200}, - Title = {{AnCora: Multilevel Annotated Corpora for Catalan and Spanish}}, + Title = {{AnCora: Multilevel Annotated Corpora for {C}atalan and {S}panish}}, Year = {2008}} @book{Taylor+94, @@ -19816,7 +19816,7 @@ @inproceedings{Thielen95 Author = {C. Thielen}, Booktitle = {Proceedings of EACL-95}, Comment = {similarity measures}, - Title = {An Approach to Proper Name Tagging for German}, + Title = {An Approach to Proper Name Tagging for {G}erman}, Year = 1995} @inproceedings{Thompson+99, @@ -20017,7 +20017,7 @@ @incollection{Tranel95 Editor = {J. A. Goldsmith}, Pages = {798--816}, Publisher = {Blackwell}, - Title = {Current issues in French phonology}, + Title = {Current issues in {F}rench phonology}, Year = 1995} @article{Treiman+90, @@ -20137,7 +20137,7 @@ @inproceedings{Tzoukermann94 Booktitle = {Proceedings of the Second {{\sc esca/ieee}} Workshop on Speech Synthesis, New York}, Organization = {{{\sc esca/ieee}}}, Pages = {179--182}, - Title = {Text-to-Speech for French}, + Title = {Text-to-Speech for {F}rench}, Year = 1994} @book{Uitdenboogaard75, @@ -20515,7 +20515,7 @@ @inbook{VandenBosch+07e Keywords = {ilk, Arabic, part-of-speech tagging, morphological analysis}, Pages = {203--219}, Publisher = {Springer Verlag}, - Title = {Memory-based morphological analysis and part-of-speech tagging of Arabic}, + Title = {Memory-based morphological analysis and part-of-speech tagging of {A}rabic}, Year = {2007}, Bdsk-Url-1 = {http://ilk.uvt.nl/downloads/pub/papers/P3-C11-Jan07.pdf}} @@ -20729,7 +20729,7 @@ @article{VandenBosch06 Keywords = {ilk, spelling, grapheme-phoneme conversion, morphological analysis}, Number = 1, Pages = {25--44}, - Title = {Spelling space: A computational test bed for phonological and morphological changes in Dutch spelling}, + Title = {Spelling space: A computational test bed for phonological and morphological changes in {D}utch spelling}, Volume = 9, Year = 2006, Bdsk-Url-1 = {http://ilk.uvt.nl/downloads/pub/papers/Spelling-space.pdf}} @@ -21060,7 +21060,7 @@ @inproceedings{Voutilainen93 Author = {A. Voutilainen}, Booktitle = {Proceedings of the 9th Nordiska Datalingvistikdagarna}, Place = {Stockholm}, - Title = {A Noun Phrase Parser of English}, + Title = {A Noun Phrase Parser of {E}nglish}, Year = 1993} @inproceedings{Voutilainen93b, @@ -21486,7 +21486,7 @@ @article{Wilks75a Note = {reprinted in RNLP}, Number = 5, Pages = {264--274}, - Title = {An intelligent analyzer and understander of English}, + Title = {An intelligent analyzer and understander of {E}nglish}, Volume = 18, Year = 1975} @@ -21815,7 +21815,7 @@ @inproceedings{Wulf96 Author = {D. Wulf}, Booktitle = {Proceedings of the Twelfth Northwest Linguistics Conference. Working Papers in Linguistics}, Pages = {239--254}, - Title = {An Analogical Approach to Plural Formation in German}, + Title = {An Analogical Approach to Plural Formation in {G}erman}, Volume = 14, Year = 1996} @@ -21976,7 +21976,7 @@ @inproceedings{Zanchetta05 Author = {Eros Zanchetta and Marco Baroni}, Booktitle = {Proceedings of the Corpus Linguistics 2005 conference}, Keyword = {NLP; corpus}, - Title = {Morph-it!: a free corpus-based morphological resource for the Italian language}, + Title = {Morph-it!: a free corpus-based morphological resource for the {I}talian language}, Year = 2005} @inproceedings{Zavrel+00, @@ -22307,7 +22307,7 @@ @phdthesis{Feist08 Author = {J.M. Feist}, Date-Modified = {2011-06-19 16:14:52 +0200}, School = {The University of Auckland}, - Title = {The order of premodifiers in English nominal phrases}, + Title = {The order of premodifiers in {E}nglish nominal phrases}, Year = 2008} @inproceedings{Mitchell09, @@ -22345,3 +22345,106 @@ @inproceedings{DeJong83b Pages = {229--246}, Title = {Sommige niet, andere wel; de verklaring van een raadselachtig verschil.}, Year = {1983}} + +% --- New entries for Section "Applications of TiMBL" (2016-2026) --- +% Each cited work was verified to actually USE TiMBL (or a TiMBL-based +% component such as Mbt), not merely cite it. + +@article{VandenBosch+25, + Author = {A. {Van den Bosch} and A. {Risco Pat\'on} and T. Buijse and P. Berck and M. {Van Gompel}}, + Journal = {arXiv preprint arXiv:2510.22317}, + Title = {Memory-based language models: An efficient, explainable, and eco-friendly approach to large language modeling}, + Year = 2025} + +@article{Jaiswal+16, + Author = {S. Jaiswal and S. K. Dhanda and M. A. Iquebal and V. Arora and T. M. Shah and U. B. Angadi and C. G. Joshi and G. P. S. Raghava and A. Rai and D. Kumar}, + Journal = {Current Research in Bioinformatics}, + Number = 1, + Pages = {10--17}, + Title = {{BIS-CATTLE}: A web server for breed identification using microsatellite {DNA} markers}, + Volume = 5, + Year = 2016} + +@inproceedings{DeSmedt+11, + Address = {Berlin}, + Author = {T. {De Smedt} and L. Lechat and W. Daelemans}, + Booktitle = {Applications of Evolutionary Computation (EvoApplications 2011), Part II}, + Editor = {C. {Di Chio} and others}, + Pages = {264--272}, + Publisher = {Springer}, + Series = {Lecture Notes in Computer Science}, + Title = {Generative art inspired by nature, using {NodeBox}}, + Volume = 6625, + Year = 2011} + +@inproceedings{Tezcan+16, + Address = {Berlin, Germany}, + Author = {A. Tezcan and V. Hoste and L. Macken}, + Booktitle = {Proceedings of the First Conference on Machine Translation (WMT), Volume 2: Shared Task Papers}, + Pages = {843--850}, + Publisher = {Association for Computational Linguistics}, + Title = {{UGENT-LT3} {SCATE} submission for the {WMT16} shared task on quality estimation}, + Year = 2016} + +@article{Daems+17, + Author = {J. Daems and O. {De Clercq} and L. Macken}, + Journal = {Linguistica Antverpiensia, New Series -- Themes in Translation Studies}, + Pages = {89--103}, + Title = {Translationese and post-editese: How comparable is comparable quality?}, + Volume = 16, + Year = 2017} + +@article{Shenoy+17, + Author = {G. G. Shenoy and E. H. Dsouza and S. K{\"u}bler}, + Journal = {arXiv preprint arXiv:1703.02019}, + Title = {Performing stance detection on {T}witter data using computational linguistics techniques}, + Year = 2017} + +@inproceedings{Chen+19, + Address = {Minneapolis, Minnesota}, + Author = {Y. Chen and J. Chen}, + Booktitle = {Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)}, + Pages = {149--156}, + Publisher = {Association for Computational Linguistics}, + Title = {A $k$-nearest neighbor approach towards multi-level sequence labeling}, + Year = 2019} + +@inproceedings{Griebenouw+19, + Address = {Vanderbijlpark, South Africa}, + Author = {A. Griebenouw and G. Drevin and D. Snyman}, + Booktitle = {2019 International Multidisciplinary Information Technology and Engineering Conference (IMITEC)}, + Pages = {1--6}, + Publisher = {IEEE}, + Title = {A combination part of speech tagger using selected voting methods}, + Year = 2019} + +@article{Zee+21, + Author = {T. Zee and L. {ten Bosch} and I. Plag and M. Ernestus}, + Journal = {Frontiers in Psychology}, + Pages = {720017}, + Title = {Paradigmatic relations interact during the production of complex words: Evidence from variable plurals in {D}utch}, + Volume = 12, + Year = 2021} + +@article{VanCraenenbroeck+19, + Author = {J. {Van Craenenbroeck} and M. {Van Koppen} and A. {Van den Bosch}}, + Journal = {Language}, + Number = 2, + Pages = {333--370}, + Title = {A quantitative-theoretical analysis of syntactic microvariation: Word order in {D}utch verb clusters}, + Volume = 95, + Year = 2019} + +@phdthesis{Pijpops19, + Author = {D. Pijpops}, + School = {University of Leuven}, + Title = {How, why and where does argument structure vary? A usage-based investigation into the {D}utch transitive-prepositional alternation}, + Year = 2019} + +@article{VanCraenenbroeck+23, + Author = {J. {Van Craenenbroeck} and M. {Van Koppen}}, + Journal = {Catalan Journal of Linguistics}, + Pages = {71--95}, + Title = {Parameters and language contact: Morphosyntactic variation in {D}utch dialects}, + Volume = 22, + Year = 2023}