@Article{apertium2010, author = {Mikel L. Forcada and Mireia Ginestí i Rosell and Jacob Nordfalk and Jim O'Regan and Sergio Ortiz-Rojas and Juan Antonio Pérez-Ortiz and Gema Ramírez-Sánchez and Felipe Sánchez-Martínez and Francis M. Tyers}, title = {Apertium: a free/open-source platform for rule-based machine translation platform}, journal = {Machine Translation}, year = 2010, note = {\textit{to appear}} } @article{apertium/2011, title = {Apertium: a free/open-source platform for rule-based machine translation}, issn = {0922-6567}, shorttitle = {Apertium}, url = {http://www.springerlink.com/content/h134p1j73377071k/export-citation/}, doi = {10.1007/s10590-011-9090-0}, journal = {Machine Translation}, author = {Forcada, Mikel L. and {Ginestí-Rosell}, Mireia and Nordfalk, Jacob and {O’Regan}, Jim and {Ortiz-Rojas}, Sergio and {Pérez-Ortiz}, Juan Antonio and {Sánchez-Martínez}, Felipe and {Ramírez-Sánchez}, Gema and Tyers, Francis M.}, month = {jul}, year = {2011} } @article{badr2009, title={Hyper-minimizing minimized deterministic finite state automata}, author={Badr, Andrew and Geffert, Viliam and Shipman, Ian}, journal={RAIRO-Theoretical Informatics and Applications}, volume={43}, number={01}, pages={69--94}, year={2009}, publisher={Cambridge Univ Press} } @article{bohnet2013joint, title={Joint Morphological and Syntactic Analysis for Richly Inflected Languages}, author={Bohnet, Bernd and Nivre, Joakim and Boguslavsky, Igor and Ginter, Rich{\'a}rd Farkas Filip and Hajic, Jan}, journal={Transactions of the Associtation for Computational Linguistics}, volume={1}, year={2013} } @article{brzozowski/1964, author = {Brzozowski, Janusz A.}, title = {Derivatives of Regular Expressions}, journal = {J. ACM}, volume = {11}, issue = {4}, month = {October}, year = {1964}, issn = {0004-5411}, pages = {481--494}, numpages = {14}, doi = {http://doi.acm.org/10.1145/321239.321249}, acmid = {321249}, publisher = {ACM}, address = {New York, NY, USA}, } @article{church/1991, author = {K. Church and W. Gale}, title = {Probability Scoring for Spelling Correction}, journal = {Statistics and Computing}, pages = {93--103}, year = {1991} } @article{Creutz07ACMTSLP, author = {Mathias Creutz and Krista Lagus}, journal = {ACM Transactions on Speech and Language Processing}, month = {January}, number = {1}, title = {Unsupervised models for Morpheme segmentation and morphology learning}, volume = {4}, year = {2007}, } @ARTICLE{damerau/1964, author = {F J Damerau}, title = {A technique for computer detection and correction of spelling errors}, journal = {Commun. ACM}, year = {1964}, number = {7} } @article{DBLP:journals/coling/Oflazer96, author = {Kemal Oflazer}, title = {Error-tolerant Finite-state Recognition with Applications to Morphological Analysis and Spelling Correction}, journal = {Computational Linguistics}, volume = {22}, number = {1}, year = {1996}, pages = {73-89}, bibsource = {DBLP, http://dblp.uni-trier.de} } @ARTICLE{deorowicz/2005, author = {Sebastian Deorowicz and Marcin G. Ciura}, title = {Correcting Spelling Errors by Modeling their Causes}, journal = {International Journal of Applied Mathematics and Computer Science}, year = {2005}, volume = {15}, pages = {275--285} } @article{hedlund/2002, author = {A Pirkola and T Hedlund and H Keskustalo}, title = {Dictionary-based cross-language information retrieval: problems, methods and research findings}, journal = {Inf. Retrieval}, year = {2001}, number = {4}, pages = {209--230} } @article{hfst/2011, title = {{HFST}--Framework for Compiling and Applying Morphologies}, author = {Krister Lind\'{e}n and Erik Axelson and Sam Hardwick and Miikka Silfverberg and Tommi Pirinen}, year = {2011}, booktitle = {Proceedings of Second International Workshop on Systems and Frameworks for Computational Morphology}, pages = {67--85}, crossref = {conf/sfcm/2011}, uri = {http://www.helsinki.fi/\%7Etapirine/publications/Pirinen-sfcm-2011.pdf} } @article{hulden/2009, author = {M{\aa}ns Huld{\'e}n}, year = {2009}, title = {Fast approximate string matching with finite automata}, journal = {Procesamiento del Lenguaje Natural}, volume = {43}, pages = {57--64} } @article{huovelinsoftware, title={Software Newsroom-an approach to automation of news search and editing}, author={Huovelin, Juhani and Gross, Oskar and Solin, Otto and Lind{\'e}n, Krister and Maisala, Sami and Oittinen, Tero and Toivonen, Hannu and Niemi, Jyrki and Silfverberg, Miikka}, year={2013}, } @article{jiang1993, author = {Jiang, Tao and Ravikumar, B.}, title = {Minimal NFA Problems Are Hard}, journal = {SIAM J. Comput.}, issue_date = {Dec. 1993}, volume = {22}, number = {6}, month = dec, year = {1993}, issn = {0097-5397}, pages = {1117--1141}, numpages = {25}, url = {http://dx.doi.org/10.1137/0222067}, doi = {10.1137/0222067}, acmid = {165076}, publisher = {Society for Industrial and Applied Mathematics}, address = {Philadelphia, PA, USA}, keywords = {Np-complete, PSPACE-complete, finite automaton, minimization}, } @article{karttunen2006numbers, title={Numbers and Finnish numerals}, author={Karttunen, Lauri}, journal={SKY Journal of Linguistics}, volume={19}, pages={407--421}, year={2006}, publisher={Citeseer} } @article{Kukich/1992/deaf, author = {Kukich, Karen}, title = {Spelling correction for the telecommunications network for the deaf}, journal = {Commun. ACM}, issue_date = {May 1992}, volume = {35}, number = {5}, month = may, year = {1992}, issn = {0001-0782}, pages = {80--90}, numpages = {11}, url = {http://doi.acm.org/10.1145/129875.129882}, doi = {10.1145/129875.129882}, acmid = {129882}, publisher = {ACM}, address = {New York, NY, USA}, keywords = {spelling correction, telecommunications network for the deaf, text-to-speech synthesis}, } @article{kukich/1992, author = {Kukich, Karen}, title = {Techniques for automatically correcting words in text}, journal = {ACM Comput. Surv.}, volume = {24}, number = {4}, year = {1992}, issn = {0360-0300}, pages = {377--439}, doi = {http://doi.acm.org/10.1145/146370.146380}, publisher = {ACM}, address = {New York, NY, USA}, } @article{levenshtein/1965, author = {В.И. Левенштейн}, year = {1965}, title = {Двоичные коды с исправлением выпадений, вставок и замещений символов}, journal = {Доклады Академий Наук СCCP}, volume = {163}, number = {4}, pages = {845–8} } @article{levenshtein/1966, author = {V. I. Levenshtein}, title = {Binary codes capable of correcting deletions, insertions, and reversals}, journal = {Soviet Physics---Doklady 10, 707–710. Translated from Doklady Akademii Nauk SSSR}, year = {1966}, pages = {845--848} } @article{linden2008assigning, title={Assigning an Inflectional Paradigm using the Longest}, author={Lind{\'e}n, Krister}, year={2008} } @article{linden2009entry, title={Entry generation by analogy—encoding new words for morphological lexicons}, author={Lind{\'e}n, Krister}, year={2009}, booktitle={Northern European Journal of Language Technology}, volume={1}, pages={1--25}, } @article{Mackenzie/HCI/2002, author={Scott MacKenzie, William Soukoreff}, title={Text Entry for Mobile Computing: Models and Methods, Theory and Practice}, journal={Human-Computer Interaction}, year={2002}, volume={17}, number={1 \& 2}, pages={147--198} } @article{maletti2011, author = {Andreas Maletti and Daniel Quernheim}, title = {Optimal Hyper-Minimization}, journal = {Int. J. Found. Comput. Sci.}, volume = {22}, number = {8}, year = {2011}, pages = {1877-1891}, ee = {http://dx.doi.org/10.1142/S0129054111009094}, bibsource = {DBLP, http://dblp.uni-trier.de} } @ARTICLE{marcus/1993, author = {Mitchell P. Marcus and Beatrice Santorini and Mary Ann Marcinkiewicz}, title = {Building a Large Annotated Corpus of {English}: The {Penn} {Treebank}}, journal = {Computational Linguistics}, year = {1993}, volume = {19}, number = {2}, pages = {313--330} } @article{mays/1991, author = {Mays, Eric and Damerau, Fred J. and Mercer, Robert L.}, title = {Context based spelling correction}, journal = {Inf. Process. Manage.}, volume = {27}, number = {5}, year = {1991}, issn = {0306-4573}, pages = {517--522}, doi = {http://dx.doi.org/10.1016/0306-4573(91)90066-U}, publisher = {Pergamon Press, Inc.}, address = {Tarrytown, NY, USA}, } @article{Mitton/1987, author = {Mitton, Roger}, title = {Spelling checkers, spelling correctors and the misspellings of poor spellers}, journal = {Inf. Process. Manage.}, issue_date = {Sept. 1987}, volume = {23}, number = {5}, month = sep, year = {1987}, issn = {0306-4573}, pages = {495--505}, numpages = {11}, url = {http://dx.doi.org/10.1016/0306-4573(87)90116-6}, doi = {10.1016/0306-4573(87)90116-6}, acmid = {33067}, publisher = {Pergamon Press, Inc.}, address = {Tarrytown, NY, USA}, } @article{mitton/2009, author = {Mitton, Roger}, title = {Ordering the suggestions of a spellchecker without using context*}, journal = {Nat. Lang. Eng.}, volume = {15}, number = {2}, year = {2009}, issn = {1351-3249}, pages = {173--192}, doi = {http://dx.doi.org/10.1017/S1351324908004804}, publisher = {Cambridge University Press}, address = {New York, NY, USA}, } @article{mohri/1997, author = {Mehryar Mohri}, title = {Finite-state transducers in language and speech processing}, journal = {Comp. Linguistics}, year = {1997}, number = {23}, pages = {269--311} } @article{nadeau/2007, title = {A survey of named entity recognition and classification}, author = {David Nadeau and Satoshi Sekine}, journal = {Lingvisticae Investigationes}, volume = {30}, number = {1}, pages = {3--26}, year = {2007}, publisher = {John Benjamins publishing company} } @article{oflazer/1996, author = {Kemal Oflazer}, title = {Error-tolerant Finite-state Recognition with Applications to Morphological Analysis and Spelling Correction}, journal = {Computational Linguistics}, volume = {22}, number = {1}, year = {1996}, pages = {73-89}, bibsource = {DBLP, http://dblp.uni-trier.de} } @article{pirinen2010creating, title={Creating and Weighting Hunspell Dictionaries as Finite-State Automata}, author={Pirinen, T.A. and Lindén, K. and others}, journal={Investigationes Linguisticae}, volume={21}, year={2010}, category = {thesis} } @article{pirinen/2010/il, author = {Tommi A Pirinen and Krister Lind\'{e}n}, title = {Creating and Weighting Hunspell Dictionaries as Finite-State Automata}, year = {2010}, volume = {19}, journal = {Investigationes Linguisticae} } @article{pirinen2012compiling, title={Compiling Apertium morphological dictionaries with HFST and using them in HFST applications}, author={Pirinen, T.A. and Tyers, F.M.}, journal={Language Technology for Normalisation of Less-Resourced Languages}, pages={25}, year={2012}, category = {thesis} } @article{Pollock/1984, author = {Pollock, Joseph J. and Zamora, Antonio}, title = {Automatic spelling correction in scientific and scholarly text}, journal = {Commun. ACM}, issue_date = {April 1984}, volume = {27}, number = {4}, month = apr, year = {1984}, issn = {0001-0782}, pages = {358--368}, numpages = {11}, url = {http://doi.acm.org/10.1145/358027.358048}, doi = {10.1145/358027.358048}, acmid = {358048}, publisher = {ACM}, address = {New York, NY, USA}, keywords = {dictionary lookup, similarity keys, spelling correction}, } @ARTICLE{schulz/2002, author = {Klaus Schulz and Stoyan Mihov}, title = {Fast String Correction with Levenshtein-Automata}, journal = {International Journal of Document Analysis and Recognition}, year = {2002}, volume = {5}, pages = {67--85} } @article {semantic-frame, title = {Frame semantics and the nature of language}, journal = {Annals of the New York Academy of Sciences: Conference on the Origin and Development of Language and Speech}, volume = {280}, number = {1}, year = {1976}, pages = {20-32}, author = {Fillmore, Charles J.} } @article{steinberger2006jrc, title={The JRC-Acquis: A multilingual aligned parallel corpus with 20+ languages}, author={Steinberger, Ralf and Pouliquen, Bruno and Widiger, Anna and Ignat, Camelia and Erjavec, Tomaz and Tufis, Dan and Varga, D{\'a}niel}, journal={arXiv preprint cs/0609058}, year={2006} } @article{Tantug:2010, author = {A. Cüneyd Tantu\u{g}}, title = {A Probabilistic Mobile Text Entry System for Agglutinative Languages}, journal = {IEEE Transactions on Consumer Electronics}, volume = {56}, number = {4}, issn = {0098-3063}, year = {2010} } @article{voutilainen2011finntreebank, title={FinnTreeBank: Creating a research resource and service for language researchers with Constraint Grammar}, author={Voutilainen, Atro}, journal={Constraint Grammar Applications}, pages={41}, year={2011} } @article{wintner/2008, author = {Wintner, Shuly}, title = {Strengths and weaknesses of finite-state technology: A case study in morphological grammar development}, journal = {Nat. Lang. Eng.}, volume = {14}, issue = {4}, month = {October}, year = {2008}, issn = {1351-3249}, pages = {457--469}, numpages = {13}, url = {http://portal.acm.org/citation.cfm?id=1520025.1520027}, doi = {10.1017/S1351324907004676}, acmid = {1520027}, publisher = {Cambridge University Press}, address = {New York, NY, USA}, } @article {wordnet, title = {WordNet: A Lexical Database for {English}}, journal = {Communications of the ACM}, volume = {38}, number = {11}, year = {1995}, pages = {39-41}, author = {Miller, George A.} } @article{Yannakoudakis/1983, title={An intelligent spelling error corrector}, volume={19}, url={http://linkinghub.elsevier.com/retrieve/pii/0306457383900468}, number={2}, journal={Information Processing and Management}, publisher={Elsevier}, author={Yannakoudakis, Emmanuel J and Fawthrop, D}, year={1983}, pages={101--108} } @Article{ Zanchetta_2005-1, author = "Eros Zanchetta and Marco Baroni", title = "Morph-it! A free corpus-based morphological resource for the Italian language", journal = "Corpus Linguistics 2005", year = "2005",issn = "1747-9398", volume = "1", number = "1", publisher = "University of Birmingham", address = "Birmingham, UK" } @book{Aho1986, author = {Aho, Alfred V. and Sethi, Ravi and Ullman, Jeffrey D.}, title = {Compilers: Principles, Techniques, and Tools}, year = {1986}, isbn = {0-201-10088-6}, publisher = {Addison-Wesley Longman Publishing Co., Inc.}, address = {Boston, MA, USA}, } @book{aho/2007, author = {Aho, Alfred V. and Lam, Monica S. and Sethi, Ravi and Ullman, Jeffrey D.}, title = {Compilers: Principles, Techniques, \& Tools with Gradiance}, year = {2007}, isbn = {0321547985, 9780321547989}, edition = {2nd}, publisher = {Addison-Wesley Publishing Company}, address = {USA}, } @book{beesley2003finite, title={Finite state morphology}, author={Beesley, Kenneth R and Karttunen, Lauri}, volume={18}, year={2003}, publisher={CSLI publications Stanford} } @incollection{linden2009, year={2009}, isbn={978-3-642-04130-3}, booktitle={State of the Art in Computational Morphology}, volume={41}, series={Communications in Computer and Information Science}, editor={Mahlow, Cerstin and Piotrowski, Michael}, doi={10.1007/978-3-642-04131-0_3}, title={HFST Tools for Morphology – An Efficient Open-Source Package for Construction of Morphological Analyzers}, url={http://dx.doi.org/10.1007/978-3-642-04131-0_3}, publisher={Springer Berlin Heidelberg}, author={Lind\'{e}n, Krister and Silfverberg, Miikka and Pirinen, Tommi}, pages={28-47} } @book{beesley/2003, title = {Finite State Morphology}, year = {2003}, author = {Kenneth R Beesley and Lauri Karttunen}, pages = {503}, publisher = {CSLI publications}, isbn = {978-1575864341} } @book {bnc, key = {bnc}, author = {The {BNC} Consortium}, title = {The {British} {National} {Corpus}}, edition = {Version 3 ({BNC} {XML})}, year = {2007}, publisher = {{Oxford} {University} Computing Services}, howpublished = {\url{http://www.natcorp.ox.ac.uk/}} }@incollection{Ruch/2001, author = {Ruch, Patrick and Baud, Robert and Geissbühler, Antoine and Lovis, Christian and Rassinoux, Anne-Marie and Rivière, Alain}, affiliation = {University Hospital of Geneva Medical Informatics Division Geneva}, title = {Using Part-of-Speech and Word-Sense Disambiguation for Boosting String-Edit Distance Spelling Correction}, booktitle = {Artificial Intelligence in Medicine}, series = {Lecture Notes in Computer Science}, editor = {Quaglini, Silvana and Barahona, Pedro and Andreassen, Steen}, publisher = {Springer Berlin / Heidelberg}, isbn = {}, pages = {249-257}, volume = {2101}, url = {http://dx.doi.org/10.1007/3-540-48229-6_36}, note = {10.1007/3-540-48229-6_36}, year = {2001} } @book{hopcroft2006, author = {Hopcroft, John E. and Motwani, Rajeev and Ullman, Jeffrey D.}, title = {Introduction to Automata Theory, Languages, and Computation (3rd Edition)}, year = {2006}, isbn = {0321455363}, publisher = {Addison-Wesley Longman Publishing Co., Inc.}, address = {Boston, MA, USA}, } @Book{knuth/1986, author = {Knuth, Donald}, title = {The \TeX book}, publisher = {Oxford University Press}, year = {1986}, address = {Oxford Oxfordshire}, isbn = {0201134489} } @conference{pirinen2012improving, title = {Improving Finite-State Spell-Checker Suggestions with Part of Speech N-Grams}, author = {Tommi Pirinen and Miikka Silfverberg and Krister Lindén}, year = {2012}, location = {Delhi, India}, booktitle = {IJCLA}, category = {thesis} } @article{pirinen2013quality, title = {Quality and Speed Trade-Offs in Weighted Finite-State Spell-Checking}, year = {2013}, author = {Tommi A Pirinen}, journal = {presubmitted}, note = {forthcoming???}, category = {thesis} } @conference{silfverberg/2011/cla, title = "Improving Predictive Entry of Finnish Text Messages using IRC Logs", author = "Miikka Silfverberg and Mirka Hyvärinen and Tommi Pirinen", year = "2011", pages = "69-76", } % FIXME: Article overflows with editor @proceedings{DBLP:conf/cicling/2011-1, CMTeditor = {Alexander F. Gelbukh}, title = {Computational Linguistics and Intelligent Text Processing - 12th International Conference, CICLing 2011, Tokyo, Japan, February 20-26, 2011. Proceedings, Part I}, booktitle = {CICLing (1)}, publisher = {Springer}, series = {LNCS}, volume = {6608}, year = {2011}, isbn = {978-3-642-19399-6}, ee = {http://dx.doi.org/10.1007/978-3-642-19400-9}, bibsource = {DBLP, http://dblp.uni-trier.de} } % FIXME: The publisher information makes the article overflow @book{einarsson/1976, author = {Jan Einarsson}, year = {1976}, title = {Talbankens skriftspråkskonkordans}, CMTpublisher = {Lund University: Department of Scandinavian Languages} } % foma is covered from page 272-- @phdthesis{phd/hulden/2009, title = {Finite-state machine construction methods and algorithms for phonology and morphology}, year = {2009}, author = {M{\aa}ns Huld{\'e}n}, school = {The University of Arizona}, } @inbook{hfst/2011, title = "HFST—Framework for Compiling and Applying Morphologies", publisher = "Springer", author = "Krister Lindén and Miikka Silfverberg and Erik Axelson and Sam Hardwick and Tommi Pirinen", year = "2011", editor = "Cerstin Mahlow and Michael Pietrowski", volume = "Vol. 100", isbn = "978-3-642-23137-7", series = "Communications in Computer and Information Science", pages = "67-85", booktitle = "Systems and Frameworks for Computational Morphology", } @incollection{kokkinakis/2003, author = {Dimitrios Kokkinakis}, title = {Swedish {NER} in the {Nomen Nescio} Project}, booktitle = {Nordisk Sprogteknologi -- Nordic Language Technology 2002}, pages = {379--398}, publisher = {Museum Tusculanums Forlag}, year = 2003, editor = {Henrik Holmboe}, address = {Copenhagen} } @incollection{linden2011, year={2011}, isbn={978-3-642-23137-7}, booktitle={Systems and Frameworks for Computational Morphology}, volume={100}, series={Communications in Computer and Information Science}, editor={Mahlow, Cerstin and Piotrowski, Michael}, doi={10.1007/978-3-642-23138-4_5}, title={HFST—Framework for Compiling and Applying Morphologies}, url={http://dx.doi.org/10.1007/978-3-642-23138-4_5}, publisher={Springer Berlin Heidelberg}, keywords={Finite-state libraries; finite-state morphology; natural language applications}, author={Lindén, Krister and Axelson, Erik and Hardwick, Sam and Pirinen, Tommi A and Silfverberg, Miikka}, pages={67-85} }@book{Aho1986, author = {Aho, Alfred V. and Sethi, Ravi and Ullman, Jeffrey D.}, title = {Compilers: Principles, Techniques, and Tools}, year = {1986}, isbn = {0-201-10088-6}, publisher = {Addison-Wesley Longman Publishing Co., Inc.}, address = {Boston, MA, USA}, } @InProceedings{drobac2014, author = {Drobac, Senka and Lind{\'e}n, Krister and Pirinen, Tommi A and Silfverberg, Miikka}, title = {Heuristic Hyper-minimization of Finite State Lexicons}, booktitle = {Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)}, year = {2014}, month = {May}, date = {28-30}, address = {Reykjavik, Iceland}, language = {english} } @article{rojas2005, title = {Construcci\'on y minimizaci\'on eficiente de transductores de letras a partir de diccionarios con paradigmas}, author = {Sergio Ortiz Rojas and Mikel L. Forcada and Gema Ram\'irez S\'anchez}, year = 2005, number = 35, journal = {Procesamiento del Lenguaje Natural}, pages = {51--57} } @incollection{linden2013hfst, title={HFST—a System for Creating NLP Tools}, author={Lind{\'e}n, Krister and Axelson, Erik and Drobac, Senka and Hardwick, Sam and Kuokkala, Juha and Niemi, Jyrki and Pirinen, Tommi A and Silfverberg, Miikka}, booktitle={Systems and Frameworks for Computational Morphology}, pages={53--71}, year={2013}, publisher={Springer} } @incollection{mcdonald/1996, title = {Internal and External Evidence in the Identification and Semantic Categorization of Proper Names}, author = {David D. McDonald}, booktitle = {Corpus Processing for Lexical Acquisition}, editor = {Branimir Boguraev and James Pustejovsky}, pages = {21--39}, year = {1996}, publisher = {MIT Press}, address = {Cambridge, MA} } @incollection{Ruch/2001, author = {Ruch, Patrick and Baud, Robert and Geissbühler, Antoine and Lovis, Christian and Rassinoux, Anne-Marie and Rivière, Alain}, affiliation = {University Hospital of Geneva Medical Informatics Division Geneva}, title = {Using Part-of-Speech and Word-Sense Disambiguation for Boosting String-Edit Distance Spelling Correction}, booktitle = {Artificial Intelligence in Medicine}, series = {Lecture Notes in Computer Science}, editor = {Quaglini, Silvana and Barahona, Pedro and Andreassen, Steen}, publisher = {Springer Berlin / Heidelberg}, isbn = {}, pages = {249-257}, volume = {2101}, url = {http://dx.doi.org/10.1007/3-540-48229-6_36}, note = {10.1007/3-540-48229-6_36}, year = {2001} } @inproceeding{klarlund/2002, author = {Nils Klarlund}, title = {Word n-grams for cluster keyboards}, booktitle = {Proceedings of the Workshop on Language Modeling for Text Entry Methods, 11th Conference of the European Chapter of the Association for Computational Linguistics}, year = {2003}, pages = {51--58} } @inproceedings{agata/2002, author = {Savary, Agata}, title = {Typographical Nearest-Neighbor Search in a Finite-State Lexicon and Its Application to Spelling Correction}, booktitle = {CIAA '01: Revised Papers from the 6th International Conference on Implementation and Application of Automata}, year = {2002}, isbn = {3-540-00400-9}, pages = {251--260}, publisher = {Springer-Verlag}, address = {London, UK}, } @inproceedings{beesley1998constraining, title={Constraining separated morphotactic dependencies in finite-state grammars}, author={Beesley, Kenneth R}, booktitle={Proceedings of the International Workshop on Finite State Methods in Natural Language Processing}, pages={118--127}, year={1998}, organization={Association for Computational Linguistics} } @inproceedings{beesley/1998, author = {Beesley, Kenneth R.}, title = {Constraining separated morphotactic dependencies in finite-state grammars}, year = {1998}, isbn = {975-7679-34-8}, pages = {118--127}, location = {Ankara, Turkey}, publisher = {Association for Computational Linguistics}, address = {Morristown, NJ, USA} } @INPROCEEDINGS{bouma/2000, author = {Gosse Bouma and Gertjan Van Noord and Robert Malouf}, title = {Alpino: Wide-coverage Computational Analysis of {Dutch}}, booktitle = {CLIN 2000}, CMTbooktitle = {Computational Linguistics in the Netherlands 2000: Selected Papers from the Eleventh CLIN Meeting}, volume = {8}, pages = {45--59}, year = {2000}, publisher = {Rodopi} } @inproceedings{Brants:2000, author = {Brants, Thorsten}, address = {Seattle, WA}, booktitle = {Proceedings of the Sixth Applied Natural Language Processing ({ANLP}-2000)}, interhash = {6dd30baa0609147c6cdf7d2a5817b236}, intrahash = {713b672cf5d64e89fb1e5b0fe20df316}, title = {TnT - A Statistical Part-of-Speech Tagger}, year = 2000, timestamp = {2009-11-30T17:48:31.000+0100}, keywords = {POS Tagging}, added-at = {2009-11-30T17:48:31.000+0100}, file = {:POS Tagging\\[Brants, Thorsten] Tnt - A Statistical Part-of-Speech Tagger.pdf:PDF}, owner = {CHAENIG}, biburl = {http://www.bibsonomy.org/bibtex/2713b672cf5d64e89fb1e5b0fe20df316/fluctuator} @INPROCEEDINGS{brants/2002, author = {Sabine Brants and Stefanie Dipper and Silvia Hansen and Wolfgang Lezius and George Smith}, title = {The {TIGER} Treebank}, year = {2002}, booktitle={Proceedings of the Workshop on Treebanks and Linguistic Theories}, address={Sozopol} } @inproceedings{brill/2000, author = {Brill, Eric and Moore, Robert C.}, title = {An improved error model for noisy channel spelling correction}, booktitle = {ACL '00: Proceedings of the 38th Annual Meeting on Association for Computational Linguistics}, year = {2000}, pages = {286--293}, location = {Hong Kong}, doi = {http://dx.doi.org/10.3115/1075218.1075255}, publisher = {Association for Computational Linguistics}, address = {Morristown, NJ, USA}, } @inproceedings{cavnar/1994, author = {William B. Cavnar and John M. Trenkle}, title = {N-Gram-Based Text Categorization}, booktitle = {Proceedings of SDAIR-94, 3rd Annual Symposium on Document Analysis and Information Retrieval}, year = {1994}, pages = {161--175} } @inproceedings{ Coltekin/2010, author = {Çağrı Çöltekin}, title = {A Freely Available Morphological Analyzer for Turkish}, booktitle = {Proceedings of the 7th International Conference on Language Resources and Evaluation (LREC2010)}, year = {2010}, location = {Valletta, Malta} } @inproceedings{conf/fsmnlp/Linden2009, title = {Weighting Finite-State Morphological Analyzers using HFST tools}, author = {Krister Lind{\'e}n and Tommi Pirinen}, year = {2009}, booktitle = {FSMNLP 2009}, crossref = {conf/fsmnlp/2009}, url = {http://www.ling.helsinki.fi/~klinden/pubs/fsmnlp2009weighting.pdf} } @inproceedings{conf/fsmnlp/Silfverberg2009, title = {HFST Runtime Format---A Compacted Transducer Format Allowing for Fast Lookup}, author = {Miikka Silfverberg and Krister Lind\'{e}n}, year = {2009}, booktitle = {FSMNLP 2009}, crossref = {conf/fsmnlp/2009}, url = {http://www.ling.helsinki.fi/~klinden/pubs/fsmnlp2009runtime.pdf} } @InProceedings{conf/lrec/Pirinen2010, author = {Tommi A Pirinen and Krister Lind\'{e}n}, title = {Finite-State Spell-Checking with Weighted Language and Error Models}, booktitle = {Proceedings of the Seventh SaLTMiL workshop on creation and use of basic lexical resources for less-resourced languagages}, year = {2010}, address = {Valletta, Malta}, pages = {13--18} } @inproceedings{conf/nodalida/bigert2003, author = {Johnny Bigert and Linus Ericson and Antoine Solis}, title = {AutoEval and Missplel: Two Generic Tools for Automatic Evaluation}, address = {Reykjavik, Iceland}, year = {2003}, booktitle = {Nodalida 2003}, crossref = {conf/nodalida/2003} } @inproceedings{conf/nodalida/Linden2009, title = {Weighted Finite-State Morphological Analysis of Finnish Compounds}, author = {Krister Lind{\'e}n and Tommi Pirinen}, year = {2009}, booktitle = {Nodalida 2009}, pages = {xxx---yyy}, crossref = {conf/nodalida/2009}, url = {http://www.ling.helsinki.fi/~klinden/pubs/linden09dnodalida.pdf} } @inproceedings{conf/sfcm/Linden2009, title = {HFST Tools for Morphology---An Efficient Open-Source Package for Construction of Morphological Analyzers}, author = {Krister Lind\'{e}n and Miikka Silfverberg and Tommi Pirinen}, year = {2009}, booktitle = {sfcm 2009}, pages = {28---47}, crossref = {conf/sfcm/2009}, uri = {http://www.helsinki.fi/\%7Etapirine/publications/Pirinen-sfcm-2009.pdf} } @inproceedings{creutz/2005, author = {Mathias Creutz and Krista Lagus and Krister Lind{\'e}n and Sami Virpioja}, year = {2005}, title = {Morfessor and Hutmegs: Unsupervised Morpheme Segmentation for Highly-Inflecting and Compounding Languages}, crossref = {conf/baltichlt2} } @inproceedings{DBLP:conf/cicling/Wilcox-OHearnHB08, author = {L. Amber Wilcox-O'Hearn and Graeme Hirst and Alexander Budanitsky}, title = {Real-Word Spelling Correction with Trigrams: A Reconsideration of the Mays, Damerau, and Mercer Model}, booktitle = {CICLing}, year = {2008}, pages = {605-616}, ee = {http://dx.doi.org/10.1007/978-3-540-78135-6_52}, crossref = {DBLP:conf/cicling/2008}, bibsource = {DBLP, http://dblp.uni-trier.de} } @inproceedings{Department98aprobabilistic, author = {Tom Bellman and I. Scott Mackenzie}, title = {A Probabilistic Character Layout Strategy for Mobile Text Entry}, booktitle = {Proceedings of Graphics Interface 1998}, year = {1998}, pages = {168--176} } @inproceedings{drobac/2012, author = {Drobac, Senka and Silfverberg, Miikka and Yli-Jyr{\"a}, Anssi}, title = {Implementation of Replace Rules Using Preference Operator}, booktitle = {Proceedings of the 10th International Workshop on Finite State Methods and Natural Language Processing}, month = {July}, year = {2012}, address = {Donostia--San Sebasti{\'a}n}, publisher = {Association for Computational Linguistics}, pages = {55--59}, url = {http://www.aclweb.org/anthology/W12-6210} } ## The articles making up the thesis @Inproceedings{pirinen2009weighted, Author = {Krister Lindén and Tommi Pirinen}, Booktitle = {Nodalida 2009}, series = {NEALT Proceedings}, volume = {4}, editor = {Kristiina Jokinen and Eckhard Bick}, Title = {Weighted Finite-State Morphological Analysis of {Finnish} Compounds}, URL = {http://www.ling.helsinki.fi/klinden/pubs/linden09dnodalida.pdf}, Year = {2009}, category = {thesis} } @inproceedings{foma, author = {Huld\'en, M{\aa}ns}, title = {Foma: a finite-state compiler and library}, booktitle = {Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics: Demonstrations Session}, series = {EACL '09}, year = {2009}, location = {Athens, Greece}, pages = {29--32}, numpages = {4}, url = {http://dl.acm.org/citation.cfm?id=1609049.1609057}, acmid = {1609057}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg, PA, USA}, } @inproceedings{Forcada01corpus-basedstochastic, author = {Mikel L. Forcada}, title = {Corpus-based stochastic finite-state predictive text entry for reduced keyboards: Application to Catalan.}, booktitle = {In Procesamiento del Lenguaje Natural}, year = {2001}, pages = {27--65} } @inproceedings{framenet, author = {Baker, Collin F. and Fillmore, Charles J. and Lowe, John B.}, title = {The {Berkeley} {FrameNet} Project}, booktitle = {Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 1}, series = {ACL '98}, year = {1998}, location = {Montreal, Quebec, Canada}, pages = {86--90}, numpages = {5}, url = {http://dx.doi.org/10.3115/980845.980860}, doi = {10.3115/980845.980860}, acmid = {980860}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg, PA, USA} } @inproceedings{ganslandt/2009, author = {Sebastian Ganslandt and Jakob Jörwall and Pierre Nugues}, title = {Predictive text entry using syntax and semantics}, booktitle = {IWPT '09 Proceedings of the 11th International Conference on Parsing Technologies}, year = {2009}, pages = {37--48} } @inproceedings{garrido-alenda02, author = {Alicia Garrido-Alenda and Mikel L. Forcada and Rafael C. Carrasco}, title = {Incremental Construction and Maintenance of Morphological Analysers Based on Augmented Letter Transducers}, booktitle = {Proceedings of TMI 2002 (Theoretical and Methodological Issues in Machine Translation, Keihanna/Kyoto, Japan)}, pages = {53--62}, year = {2002} } @inproceedings{Golding/1996, author = {Golding, Andrew R. and Schabes, Yves}, title = {Combining Trigram-based and feature-based methods for context-sensitive spelling correction}, booktitle = {Proceedings of the 34th annual meeting on Association for Computational Linguistics}, year = {1996}, location = {Santa Cruz, California}, pages = {71--78}, numpages = {8}, url = {http://dx.doi.org/10.3115/981863.981873}, doi = {http://dx.doi.org/10.3115/981863.981873}, acmid = {981873}, publisher = {Association for Computational Linguistics}, address = {Morristown, NJ, USA}, } @inproceedings{gong/2008, author = {Jun Gong, Peter Tarasewich, I. Scott MacKenzie}, year = {2008}, title = {Improved word list ordering for text entry on ambiguous keypads}, booktitle = {Proceedings of the 5th Nordic conference on Human-computer interaction: building bridges}, year = {2008}, pages = {132--161} } @inproceedings{Harbusch/2003, author = {Karin Harbusch and Sasa Hasan and Hajo Hoffmann and Michael Kühn and Bernhard Schüler}, title = {Domain-specific disambiguation for typing with ambiguous keyboards}, booktitle = {Proceedings of the EACL Workshop}, year = {2003} } @inproceedings{hassan/2008, author = {Ahmed Hassan and Sara Noeman and Hany Hassan}, title = {Language Independent Text Correction using Finite State Automata}, year = {2008}, booktitle = {Proceedings of the Third International Joint Conference on Natural Language Processing}, volume = {2}, location = {Hyderabad, India}, pages = {913--918} } @inproceedings{hfst/2011, author = {Lind\'{e}n, Krister and Axelson, Erik and Hardwick, Sam and Pirinen, Tommi A and Silfverberg, Miikka}, editor = {Cerstin Mahlow and Michael Piotrowski}, booktitle = {Systems and Frameworks for Computational Morphology}, title = {{H}{F}{S}{T}—Framework for Compiling and Applying Morphologies}, publisher = {Springer}, year = 2011, key = {Computer Science}, volume = 100, series = {Communications in Computer and Information Science}, address = {Berlin Heidelberg}, pages = {67--85}, } @inproceedings{hfst/2012/cla, author = {Krister Lind\'{e}n and Erik Axelson and Senka Drobac and Sam Hardwick and Miikka Silfverberg and Tommi A Pirinen}, title = {Using HFST for Creating Computational Linguistic Applications}, booktitle = {Proceedings of Computational Linguistics - Applications, 2012}, pages = {to appear}, year = {2012} } @inproceedings{how05optimizing, author = {Yijue How and Min-Yen Kan}, booktitle = {Proc. of Human Computer Interfaces International (HCII 05)}, editor = {M. J. Smith and G. Salvendy}, interhash = {ba12ca2c9a4f61c3543978b99ab5d5ca}, intrahash = {d3dd5c65f8d41d4c4f952811013509db}, publisher = {Lawrence Erlbaum Associates}, title = {Optimizing Predictive Text Entry for Short Message Service on Mobile Phones}, year = 2005, timestamp = {2007-03-23T14:55:11.000+0100}, keywords = {sms text-mining}, added-at = {2007-03-23T14:55:11.000+0100}, location = {Las Vegas, US}, isbn = {0805858075}, biburl = {http://www.bibsonomy.org/bibtex/2d3dd5c65f8d41d4c4f952811013509db/sb3000}, month = {July} } @inproceedings{karlsson/1990/cg, author = {Fred Karlsson}, year = {1990}, title = {Constraint Grammar as a Framework for Parsing Unrestricted Text}, editor = {H. Karlgren}, booktitle = {Proceedings of the 13th International Conference of Computational Linguistics}, volume = {3}, address= {Helsinki}, pages = {168--173} } @inproceedings{karlsson/1990, author = {Fred Karlsson}, year = {1990}, title = {Constraint Grammar as a Framework for Parsing Unrestricted Text}, editor = {H. Karlgren}, booktitle = {Proceedings of the 13th International Conference of Computational Linguistics}, volume = {3}, address= {Helsinki}, pages = {168--173} } @inproceedings{karlsson/1992, author = {Fred Karlsson}, title = {SWETWOL: A Comprehensive Morphological Analy