| |
|
|
| |
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
2011
Extending memory-based machine translation to phrases
Author(s): Maarten van Gompel, Antal van den Bosch, and Peter Berck
Reference: In T. Markus, P. Monachesi, and E. Westerhout
(Eds.), Computational Linguistics in the Netherlands 2010: Selected
Papers from the Twentieth CLIN Meetin. Utrecht, LOT: pp. 45-58.
[pdf]
Paraphrasing headlines by machine translation
Author(s): Sander Wubben, Antal van den Bosch, and Emiel Krahmer
Reference: In T. Markus, P. Monachesi, and E. Westerhout
(Eds.), Computational Linguistics in the Netherlands 2010: Selected
Papers from the Twentieth CLIN Meetin. Utrecht, LOT: pp. 169-183.
[pdf]
Enrichment and structuring of archival description metadata
Author(s): Kalliopi Zervanou, Ioannis Korkontzelos, Antal van den Bosch, and Sophia Ananiadou
Reference: In K. Zervanou and P. Lendvai (Eds.), Proceedings of the Fifth ACL-HLT Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities (LaTeCH-2011), Portland, OR, pp. 44-53.
[pdf]
Comparing phrase-based and syntax-based paraphrase generation
Author(s): Sander Wubben, Erwin Marsi, Antal van den Bosch, and Emiel Krahmer
Reference: In K. Filippova and S. Wan (Eds.), Proceedings of the ACL-HLT Workshop on Text-to-Text Generation, Portland, OR, pp. 27-33.
[pdf]
A link to the past: Constructing historical social networks
Author(s): Matje van de Camp and Antal van den Bosch
Reference: In A. Balahur, E. Boldrini, A. Montoyo, and P. Martinez-Barco (Eds.), Proceedings of the ACL-HLT Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (WASSA-2011), Portland, OR, pp. 61-69.
[pdf]
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
2010
Paraphrase Generation as Monolingual Translation: Data and Evaluation
Author(s): Sander Wubben, Antal van den Bosch, and Emiel Krahmer
Reference: In J. Kelleher, B. Mac Namee and I. van der Sluis (Eds.) Proceedings of the 10th International Workshop on Natural Language Generation (INLG 2010), Dublin, Ireland, pp. 203-207.
[pdf]
Memory-based learning
Author(s): Walter Daelemans and Antal van den Bosch
Reference: In A. Clark, C. Fox, and S. Lappin (Eds.), Handbook of Computational Linguistics and Natural Language Processing. Oxford, UK: Wiley-Blackwell Publishers, pp. 154-179.
[book website]
On the evaluation of entity profiles
Author(s): Maarten de Rijke, Krisztian Balog, Toine Bogers, and Antal van den Bosch
Reference: In CLEF 2010: Conference on Multilingual and Multimodal Information Access Evaluation, pp. 94-99.
[pdf]
Beyond reported history: Strikes that never happened
Author(s): Martha van den Hoven, Antal van den Bosch, and Kalliopi Zervanou
Reference: In S. Darányi and P. Lendvai (Eds.), Proceedings of the First International AMICUS Workshop on Automated Motif Discovery in Cultural Heritage and Scientific Communication Texts, Vienna, Austria, pp. 20-28.
[pdf]
A Kid's Open Mind Common Sense
Author(s): Antal van den Bosch, Pim Nauts, and Nienke Eckhardt
Reference: In Commonsense Knowledge: Papers from the AAAI Fall Symposium, pp. 114-119
[pdf]
Supertags as source language context in hierarchical phrase-based SMT
Author(s): Rejwanul Haque, Sudip Kumar Naskar, Antal van den Bosch and Andy Way
Reference: In Proceedings of AMTA 2010: The Ninth Conference of the Association for Machine Translation in the Americas, Denver, CO., pp. 210-219
[pdf]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009
Putting the t where it belongs: Solving a confusion problem in Dutch
Author(s): Herman Stehouwer and Antal van den Bosch
Reference: In S. Verberne, H. van Halteren, and P.-A. Coppen (Eds.), Computational Linguistics in the Netherlands 2007: Selected Papers from the 18th CLIN Meeting, January 22, 2009, Groningen, pp. 21-36.
[pdf]
Memory-based machine translation and language modeling
Author(s): Antal van den Bosch and Peter Berck
Reference: The Prague Bulletin of Mathematical Linguistics No. 91, pp. 17-26.
[pdf]
Using language modeling for spam detection in social reference
manager websites
Author(s): Toine Bogers and Antal van den Bosch
Reference: In R. Aly, C. Hauff, I. den Hamer, D. Hiemstra,
T. Huibers, and F. de Jong (Eds.), Proceedings of the 9th
Belgian-Dutch Information Retrieval Workshop (DIR 2009), pp 87-94.
[pdf]
A semantic relatedness metric based on free link structure
Author(s): Sander Wubben and Antal van den Bosch
Reference: In H.C. Bunt, V. Petukhova, and S. Wubben (Eds.), Proceedings of the Eighth International Conference on Computational Semantics (IWCS-8), pp. 355-359.
[pdf]
Instance-driven discovery of ontological relation labels
Author(s): Marieke van Erp, Antal van den Bosch, Sander Wubben, and Steve Hunt
Reference: Proceedings of the EACL 2009 Workshop on Language Technology and Resources for Cultural Heritage, Social Sciences, Humanities, and Education (LaTeCH -- SHELT&R 2009), Athens, Greece, pp. 60-68.
[pdf]
Clustering and matching headlines for automatic paraphrase acquisition
Author(s): Sander Wubben, Antal van den Bosch, Emiel Krahmer, and Erwin Marsi
Reference: In E. Krahmer and M. Theune (Eds.), Proceedings of the 12th European Workshop on Natural Language Generation (ENLG 2009), Athens, Greece, pp. 122-125.
[pdf]
Making a clean sweep of cultural heritage
A constraint satisfaction approach to machine translation
Author(s): Sander Canisius and Antal van den Bosch
Reference: In In H. Somers and L. Màrquez (Eds.), Proceedings of the 13th Annual Conference of the European Association for Machine Translation (EAMT-2009), pp. 182-189.
[pdf]
Joint memory-based learning of syntactic and semantic dependencies in multiple languages
Author(s): Roser Morante, Vincent Van Asch, and Antal van den Bosch
Reference: In Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL): Shared Task, pp. 25-30. Stroudsburg, PA: Association for Computational Linguistics.
[pdf]
Digital discoveries in museums, libraries, and archives: Computer
science meets cultural heritage
Author(s): Antal van den Bosch, Jaap van den Herik, and Paul Doorenbosch
Reference: Interdisciplinary Science Review, 34:2-3, pp. 129-138.
[pdf]
Weaving a new fabric of natural history
Author(s): Antal van den Bosch, Piroska Lendvai, Marieke van Erp, Steve Hunt, Marian van der Meij, and René Dekker
Reference: Interdisciplinary Science Review, 34:2-3, pp. 206-223.
[pdf]
Dependency parsing and semantic role labeling as a single task
Extending memory-based machine translation to phrases
Dependency relations as source context in phrase-based SMT
Author(s): Rejwanul Haque, Sudip Kumar Naskar, Antal van den Bosch, and Andy Way
Reference: In Proceedings of PACLIC 23: the 23rd Pacific Asia Conference on Language, Information and Computation, Hong Kong, China, pp.170-179.
[pdf]
Collaborative and content-based filtering for item recommendation on social bookmarking websites
Author(s): Toine Bogers and Antal van den Bosch
Reference: In D. Jannach, W. Geyer, J. Freyne, S. S. Anand,
C. Dugan, B. Mobasher, and A. Kobsa (Eds.), Proceedings of the ACM
RecSys '09 workshop on Recommender Systems and the Social Web,
pp. 9-16, October 2009.
[pdf]
Feature construction for memory-based semantic role labeling of Catalan and Spanish
Author(s): Roser Morante and Antal van den Bosch
Reference: In N. Nicolov, G. Angelova, and R. Mitkov (Eds.), Recent Advances in Natural Language Processing V, Current Issues in Linguistic Theory 309, pp. 131-142. Amsterdam, the Netherlands: John Benjamins.
[publisher's webpage]
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
2008
A modular approach to learning Dutch co-reference
Author(s): Véronique Hoste and Antal van den Bosch
Reference: In C. Johansson (Ed.), Proceedings from the First Bergen Workshop on Anaphora Resolution (WAR I), Bergen, Norway, pp. 51-75.
[pdf]
Using citation analysis for expert retrieval in workgroups
Author(s): Toine Bogers, Klaas Kox, and Antal van den Bosch
Reference: In E. Hoenkamp, M. de Cock, and V. Hoste (Eds.), Proceedings of the 8th Belgian-Dutch Information Retrieval Workshop (DIR 2008), pp 21-28. Maastricht, April 2008.
[pdf]
A Personalized Recommender System for Writing in the Internet Age
Author(s): Mari Carmen Puerta Melguizo, Olga Munoz Ramos, Lou Boves, Toine Bogers, and Antal van den Bosch
Reference: In Proceedings of the LREC 2008 Workshop on Natural Language Processing Resources, Algorithms, and Tools for Authoring Aid. Marrakech, Morocco, 2008.
Efficient Context-Sensitive Word Completion for Mobile Devices
Author(s): Antal van den Bosch and Toine Bogers
Reference: In MobileHCI 2008: Proceedings of the 10th International Conference on Human-Computer Interaction with Mobile Devices and Services, IOP-MMI special track, pp 465-470. Amsterdam, The Netherlands, September 2008.
[pdf]
Using Language Models for Spam Detection in Social Bookmarking
Author(s): Toine Bogers and Antal van den Bosch
Reference: In Proceedings of 2008 ECML/PKDD Discovery Challenge Workshop, pp 1-12. Antwerp, Belgium, September 2008.
[pdf]
Recommending Scientific Articles using CiteULike
Author(s): Toine Bogers and Antal van den Bosch
Reference: In RecSys '08: Proceedings of the 2008 ACM Conference on Recommender Systems, pp 287-290, ACM Press, October 2008.
[pdf]
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
2007
A memory-based classification approach to marker-based EBMT
Author(s): Antal van den Bosch, Nicolas Stroppa, and Andy Way
Reference: In F. Van Eynde, V. Vandeghinste, and I. Schuurman (Eds.), Proceedings of the METIS-II Workshop on New Approaches to Machine Translation, 63-72. January 11, 2007, Leuven, Belgium.
[pdf]
Superlinear parallelisation of the k-nearest neighbor classifier
Author(s): Antal van den Bosch and Ko van der Sloot
Reference: In P. Adriaans, M. van Someren, and S. Katrenko (Eds.), Proceedings of the 18th BENELEARN Conference. May 14, 2007, Amsterdam, The Netherlands.
[pdf]
Automatic techniques for generating and correcting cultural heritage collection metadata
Author(s): Antal van den Bosch, Caroline Sporleder, Marieke van
Erp, and Steve Hunt
Reference: In Proceedings of Digital
Humanities 2007, the 19th Joint International Conference of the
Association for Computers and the Humanities and the Association for
Literary and Linguistic Computing, University of Illinois at Urbana-Champaign, Illinois, US, pp. 223-224.
[online
abstract]
ILK: Machine learning of semantic relations with shallow features and almost no data
Author(s): Iris Hendrickx, Roser Morante, Caroline Sporleder,
and Antal van den Bosch
Reference: In Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007), Prague, Czech Republic, pp. 187-190.
[pdf, bib]
What a proactive recommendation system needs: Relevance, non-intrusiveness, and a new long-term memory
Author(s): Mari-Carmen Puerta Melguizo, Toine Bogers, Anita Deshpande, Lou Boves, and Antal van den Bosch
Reference: In Proceedings of the 9th International Conference on Enterprise Information Systems (ICEIS 2007), Funchal, Madeira.
[pdf]
Broad expertise retrieval for sparse data environments
Author(s): Krisztian Balog, Toine Bogers, Leif Azzopardi, Maarten de Rijke, and Antal van den Bosch
Reference: In SIGIR'07: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Amsterdam, the Netherlands, pp. 551-558.
[pdf]
Memory-based semantic role labeling of Catalan and Spanish
Author(s): Roser Morante and Antal van den Bosch
Reference: In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP-2007), Borovets, Bulgaria, pp. 388-394.
[pdf]
Recompiling a knowledge-based dependency parser into memory
Author(s): Sander Canisius and Antal van den Bosch
Reference: In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP-2007), Borovets, Bulgaria, pp. 104-108.
[pdf]
Arabic computational morphology: Knowledge-based and empirical methods
Memory-based morphological analysis and part-of-speech tagging of Arabic
Author(s): Antal van den Bosch, Erwin Marsi, and Abdelhadi Soudi
Reference: In Soudi, A., Van den Bosch, A., and Neumann, G. (Eds), Arabic computational morphology: Knowledge-based and empirical methods, Chapter 11, pp. 203-219. Berlin: Springer.
[pdf of preprint]
Comparing and evaluating information retrieval algorithms for news recommendation
Author(s): Toine Bogers and Antal van den Bosch
Reference: In Proceedings of the 2007 ACM Conference on Recommender Systems, Minneapolis, MN, pp. 141-144, ACM Press
[pdf]
Superlinear parallelization of k-nearest neighbor retrieval
Author(s): Antal van den Bosch and Ko van der Sloot
Reference: In M. Dastani and E. de Jong (Eds.), Proceedings of the 19th Belgian-Dutch Artificial Intelligence Conference (BNAIC-2007), Utrecht, The Netherlands, pp. 65-72.
[pdf]
Exploiting source similarity for SMT using context-informed features
Author(s): Nicolas Stroppa, Antal van den Bosch, and Andy Way
Reference: In A. Way
and B. Gawronska (Eds.), Proceedings of the 11th International Conference on Theoretical Issues in Machine Translation (TMI 2007), Skövde, Sweden, pp. 231-240.
[pdf]
A pilot study for semantic role labeling in a Dutch corpus
Author(s): Gerwert Stevens, Paola Monachesi, and Antal van den Bosch
Reference: In P. Dirix, I. Schuurman, V. Vandeghinste, and F. Van Eynde (Eds.), Computational Linguistics in the Netherlands: Selected Papers from the Seventeenth CLIN Meeting, Leuven, Belgium, pp. 99-114.
[preprint pdf]
An efficient memory-based morpho-syntactic tagger and parser for Dutch
Author(s): Antal van den Bosch, Bertjan Busser, Sander Canisius, and Walter Daelemans
Reference: In P. Dirix, I. Schuurman, V. Vandeghinste, and F. Van Eynde (Eds.), Computational Linguistics in the Netherlands: Selected Papers from the Seventeenth CLIN Meeting, Leuven, Belgium, pp. 99-114.
[preprint pdf]
Dat gebeurd mei niet: Computationele modellen voor verwarbare homofonen
Author(s): Walter Daelemans and Antal van den Bosch
Reference: In: Dominiek Sandra, Rita Rymenans, Pol Cuvelier, & Peter van Petegem (Eds), Tussen taal, spelling en onderwijs: Essays bij het emeritaat van Frans Daems. Gent: Academia Press, pp. 199-210, 2007
[pdf]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006
Authoritative re-ranking in fusing authorship-based subcollection
search results
Author(s): Toine Bogers and Antal van den
Bosch
Reference: In F. de Jong and W. Kraaij (Eds.), Proceedings of the Sixth Belgian-Dutch Information Retrieval Workshop, DIR-2006, pp 49-55. Enschede: Neslia Paniculata.
[pdf]
Constraint satisfaction inference: Non-probabilistic global inference for sequence labelling
Spotting the 'odd-one-out': Data-driven error detection and correction
in textual databases
Correcting 'wrong-column' errors in text databases
Authoritative re-ranking of search results
Author(s): Toine Bogers and Antal van den
Bosch
Reference: In Proceedings of the 28th European
Conference on Information Retrieval (ECIR 2006), vol. 3936 of
Lecture Notes on Computer Science, pp. 519-522. Springer Verlag, April
2006.
[pdf]
Identifying named entities in text databases from the natural history domain
Transferring PoS-tagging and lemmatization tools from spoken to written Dutch corpus development
Author(s): Antal van den Bosch, Ineke Schuurman, and Vincent Vandeghinste
Reference: In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC-06), Genoa, Italy, 2006.
[pdf]
Dependency parsing by inference over high-recall dependency predictions
Improved morpho-phonological sequence processing with constraint satisfaction inference
Author(s): Antal van den Bosch and Sander Canisius
Reference: In Proceedings of the Eighth Meeting of the ACL Special Interest Group in Computational Phonology, SIGPHON '06, June 2006, New York City, NY.
[pdf]
All-word prediction as the ultimate confusible disambiguation
Author(s): Antal van den Bosch
Reference: In Proceedings of the HLT-NAACL Workshop on Computationally hard problems and joint inference in speech and language processing, June 2006, New York City, NY.
[pdf]
A rule-based approach for process discovery: Dealing with noise and imbalance in process logs
Author(s): Laura Maruster, Ton Weijters, Wil van der Aalst, and
Antal van den Bosch
Reference: Data Mining and Knowledge Discovery,
13, pp. 67-87, 2006.
[preprint pdf]
Spelling space: A computational test bed for phonological and morphological changes in Dutch spelling
Discrete versus probabilistic sequence classifiers for domain-specific entity chunking
Expertise classification: Collaborative classification vs. automatic extraction
Author(s): Toine Bogers, Willem Thoonen, and Antal van den
Bosch
Reference: In Proceedings of the 17th Annual ASIS&T SIG/CR workshop on Social Classification, Austin, TX.
[pdf]
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
2005
Memory-based language processing
Improving sequence segmentation learning by predicting trigrams
Author(s): Antal van den Bosch and Walter Daelemans
Reference: In Proceedings of the Ninth Conference on
Natural Language Learning, CoNLL-2005, June 29-30, 2005, Ann
Arbor, MI, pp. 80-87.
[pdf]
Applying spelling error correction techniques for improving semantic role labelling
Memory-based morphological analysis generation and part-of-speech
tagging of Arabic
Author(s): Erwin Marsi, Antal van den Bosch, and Abdelhadi Soudi
Reference: In Proceedings of the ACL Workshop on
Computational Approaches to Semitic Languages, June 29, 2005, Ann
Arbor, MI.
[pdf]
Robust ASR lattice representation types in pragma-semantic processing
of spoken input
Rule meta-learning for trigram-based sequence processing
Memory-based understanding of user utterances in a spoken dialogue system: Effects of feature selection and co-learning
Author(s): Antal van den Bosch
Reference: In Workshop Proceedings of the 6th International Conference on Case-Based Reasoning, Chicago, August 2005, pp. 85-94.
[pdf]
Hybrid algorithms for instance-based classification
Author(s): Iris Hendrickx and Antal van den Bosch
Reference: In J. Gama, R. Camacho, P. Brazdil, A. Jorge,
and L. Torgo (Eds.), Machine Learning: ECML 2005: 16th European
Conference on Machine Learning, Porto, Portugal, October 3-7,
2005. Lecture Notes in Computer Science 3720. Berlin: Springer Verlag,
pp. 158-169.
[pdf]
Scalable classification-based word prediction and confusible correction
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
2004
Memory-based semantic role labeling: Optimizing features, algorithm, and output
GAMBL, genetic algorithm optimization of memory-based WSD
Author(s): Bart Decadt, Veronique Hoste, Walter Daelemans, and
Antal van den Bosch
Reference: In: R. Mihalcea and P. Edmonds (eds.),
Proceedings of the Third International Workshop on the Evaluation of
Systems for the Semantic Analysis of Text (Senseval-3), Barcelona,
Spain, July 2004, pages 108-112.
[pdf]
Feature transformation through rule induction: a case study with the
k-NN classifier
Author(s): Antal van den Bosch
Reference: In J. Fürnkrantz (Ed.), Proceedings of
the ECML/PKDD 2004 Workshop on Advances in Inductive Rule
Learning, Pisa, Italy, September 2004, pp. 1-16.
[pdf]
Memory-based robust interpretation of recognised speech
Maximum-entropy parameter estimation for the k-NN modified
value-difference kernel
Author(s): Iris Hendrickx and Antal van den Bosch
Reference: In R. Verbrugge, N. Taatgen, and L. Schomaker
(Eds.), Proceedings of the 16th Belgian-Dutch Conference on
Artificial Intelligence, Groningen, The Netherlands, pp.
[pdf]
Wrapped progressive sampling search for optimizing learning algorithm
parameters
Author(s): Antal van den Bosch
Reference: In R. Verbrugge, N. Taatgen, and L. Schomaker
(Eds.), Proceedings of the 16th Belgian-Dutch Conference on
Artificial Intelligence, Groningen, The Netherlands, pp.
[pdf]
A memory-based shallow parser for spoken Dutch
Author(s): Sander Canisius and Antal van den Bosch
Reference: In B. Decadt, G. De Pauw, and V. Hoste (Eds.),
Selected papers from the Thirteenth Computational Linguistics in
the Netherlands Meeting, Antwerp, Belgium, pp. 31-45.
[pdf]
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
2003
Learning PP attachment for filtering prosodic phrasing
Machine learning for shallow interpretation of user utterances in
spoken dialogue systems
Author(s): Piroska Lendvai, Antal van den
Bosch and Emiel Krahmer
Reference: In: Proceedings of the EACL-03 Workshop on
Dialogue Systems: Interaction, Adaptation and Styles of
Management. Budapest, 2003. pages 69-78.
[pdf] - note: corrected version!
Memory-based one-step named-entity recognition: Effects of seed list features, classifier stacking, and unannotated data
Author(s): Iris Hendrickx and Antal van den Bosch
Reference: In: Proceedings of CoNLL-2003, the Seventh Conference on Natural Language Learning, Edmonton, Canada,
2003, pp. 176-179.
[pdf]
Learning to predict pitch accents and prosodic boundaries in Dutch
Memory-based disfluency chunking
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
2002
Shallow parsing on the basis of words only: A case study
Author(s): Antal van den Bosch and Sabine Buchholz.
Reference: In Proceedings of the 40th
Meeting of the Association for Computational Linguistics (ACL'02).
(this preprint
corrects the proceedings version on three points: (1) two words in the
abstract, (2) the title of section 4, and (3) a corrected reference to
Eisner 1996)
[pdf]
Dutch word sense disambiguation: Optimizing the localness of context
Evaluating the results of a memory-based word-expert approach to
unrestricted word sense disambiguation
Improving machine-learned detection of miscommunications in human-machine dialogues through informed data splitting
Multi-feature error detection in spoken dialogue systems
Logistic-based patient grouping for multi-disciplinary treatment
Process Mining: Discovering Direct Successors in Process Logs
Author(s): Laura Maruster, Ton Weijters, Wil van der Aalst, and
Antal van den Bosch
Reference: In S. Lange, K. Satoh,
C.H. Smith (Eds.): Discovery Science, 5th International
Conference. Lecture Notes in Computer Science 2534. Berlin:
Springer, pp. 364-373, 2002.
[ps]
Parameter optimization for machine learning of word sense disambiguation
Combining information sources for memory-based pitch accent placement
Expanding k-NN analogy with instance families
Author(s): Antal van den Bosch
Reference: In R. Skousen, D. Lonsdale, and D. Parkinson (Eds.),
Analogical Modeling: An exemplar-based approach to
language. Amsterdam: John Benjamins, pp. 209-224.
[pdf of preprint
]
Proceedings of the Sixth Conference on Natural Language Learning (CoNLL-2002)
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
2001
Detecting problematic turns in human-machine interactions: Rule-induction versus
memory-based learning approaches
Author(s): Antal van den Bosch, Emiel Krahmer, and Marc Swerts.
Reference: In Proceedings of the 39th Meeting of the
Association for Computational Linguistics (ACL'01). New Brunswick, NJ:
ACL, pp. 499-506, 2001.
[pdf]
TreeTalk: Memory-based word phonemisation
Automatic discovery of workflow models from hospital data
Predicting phrase breaks with memory-based learning
Author(s): Bertjan Busser, Walter Daelemans, Antal van den
Bosch
Reference: In Proceedings 4th ISCA Tutorial and
Research Workshop on Speech Synthesis. Perthshire Scotland, August
29th - September 1st, 2001.
[ps]
Dutch word sense disambiguation: Data and preliminary results
Author(s): Iris Hendrickx, Antal van den
Bosch
Reference: In Proceedings of SENSEVAL-2. Toulouse, France.
[pdf]
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
2000
Integrating seed names and n-grams for a named entity list and
classifier
Learning statistically neutral tasks without expert guidance
Unpacking multi-valued
symbolic features and classes in memory-based language learning
Author(s): Antal van den Bosch and Jakub Zavrel
Referemce: In P. Langley (Ed.), Proceedings of the
Seventeenth International Conference on Machine Learning, pp.
1055-1062. San Francisco, CA: Morgan Kaufmann, 2000.
[abs, ps]
Memory-based word sense disambiguation
Author(s): Jorn Veenstra, Antal van den Bosch, Sabine Buchholz, Walter Daelemans, Jakub Zavrel
Reference: Computers and the Humanities, special issue on Senseval, Word Sense Disambiguations, Ed. Adam Kilgarriff and Martha Palmer,
34:1-2, 2000
[abs,
ps of preprint]
A distributed, yet
symbolic model of text-to-speech processing
Author(s): Antal van den Bosch and Walter Daelemans
Reference: In P. Broeder and
J.M.J. Murre (Eds.), Models of Language Acquisition: inductive and
deductive approaches. Oxford University Press, 76-99, 2000.
[abs, ps]
Using induced rules as complex features in memory-based language learning
Author(s): Antal van den Bosch
Reference: In Proceedings of the Fourth Conference on
Computational Natural Language Learning and of the Second Learning
Language in Logic Workshop (CoNLL/LLL). New Brunswick, NJ: ACL,
pp.73-78.
[ps]
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
1999
Forgetting exceptions is harmful in language learning
Interpreting knowledge representations in BP-SOM
Memory-based morphological analysis
Author(s): Antal van den Bosch and Walter Daelemans.
Reference: In: Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics, ACL'99, University of Maryland, USA, June 20-26, 1999, pp. 285-292.
[abs, pdf]
Instance-family abstraction in memory-based language learning
Author(s): Antal van den Bosch.
Reference: In: I. Bratko and S. Dzeroski (Eds.), Machine Learning: Proceedings of the Sixteenth International Conference, ICML'99, Bled, Slovenia, June 27-30, 1999, pp. 39-48.
[abs, ps]
Machine learning of word pronunciation: the case against
abstraction
Careful abstraction from instance families in memory-based language
learning
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
1998
Modularity in inductively-learned word pronunciation systems
Do not forget: Full memory in memory-based learning of word pronunciation
Rapid development of NLP modules with memory-based learning
Author(s): Walter Daelemans, Antal van den Bosch, Jakub Zavrel,
Jorn Veenstra, Sabine Buchholz, and Bertjan Busser.
Reference: In Proceedings of ELSNET in Wonderland, pp.
105-113. Utrecht: ELSNET, 1998. Also in R. Basili and M.T. Pazienza (Eds.),
ECML-98 TANLPS Workshop Notes, Technische Universitaet Chemnitz,
1998, pp. 1-17.
[abs,ps]
Interpretable neural networks with BP-SOM
Toward inductive lexicons: a case study
Author(s): Walter Daelemans, Gert Durieux, and Antal van den Bosch.
Reference: In: P. Velardi (ed.), Proceedings LREC Workshop
on Adapting Lexical and Corpus Resources to Sublanguages and Applications,
Granada, Spain, pp. 29-35, 1998.
[abs,ps]
A connectionist model for bootstrap learning of syllabic structure
Author(s): Jean Vroomen, Antal van den Bosch, and Beatrice De Gelder.
Reference: Language and Cognitive Processes, Special
issue on Language Acquisition and Connectionionism (Ed. K. Plunkett), 13:2/3,
pp. 193-220.
A connectionist model for bootstrap learning of syllabic structure
Author(s): Jean Vroomen, Antal van den Bosch, and Beatrice De Gelder.
Reference: Language and Cognitive Processes, Special
issue on Language Acquisition and Connectionionism (Ed. K. Plunkett), 13:2/3,
pp. 193-220.
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
1997
IGTree: Using trees for compression and classification in lazy learning
Algorithms
Workshop notes on empirical learning of natural language processing tasks.
Author(s): Walter Daelemans, Ton Weijters, and Antal van den
Bosch (eds.)
Reference: In M. van Someren and G. Widmer
(eds.) Machine Learning: ECML-97, Lecture Notes in Artificial
Intelligence 1224, Berlin: Springer, 337-344, 1997.
[electronic workshop notes]
Empirical learning of natural language processing tasks
Author(s): Walter Daelemans, Antal van den Bosch, and Ton Weijters.
Reference: M. van Someren and G. Widmer (eds.) Machine Learning:
ECML-97, Lecture Notes in Artificial Intelligence 1224, Berlin: Springer,
337-344, 1997.
[abs,
ps]
A feature-relevance heuristic for indexing and compressing large
case bases
Author(s): Daelemans, W., A. van den Bosch, and J. Zavrel.
Reference: M. van Someren and G. Widmer (eds.) 9th European
Conference on Machine Learning - Poster Papers. Prague: Laboratory of
Intelligent Systems, 29-38, 1997.
[abs,
ps]
Learning to pronounce written words. A study in inductive language learning
Author(s): Antal van den Bosch.
Reference: Ph.D. Thesis, Universiteit Maastricht, The Netherlands.
Cadier en Keer: Phidippides, 1997.
[ps]
Automatic phonetic transcription of words based on sparse data
Author(s): Maria Wolters and Antal van den Bosch.
Reference: In Walter Daelemans, Antal van den Bosch, and Ton Weijters (Eds.), Workshop notes of ECML/MLnet Familiarization Workshop on
Empirical Learning of Natural Language Processing Tasks, April 1997,
Prague, Czech Republic, pp. 61-70, 1997.
[abs] [ps]
When small disjuncts abound, try lazy learning: A case study
Intelligible neural networks with BP-SOM
Avoiding overfitting with BP-SOM
Behavioural aspects of BP-SOM
Het principe van de quaterniteit als algemeen denkraam
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
1996
Language-Independent Data-Oriented Grapheme-to-Phoneme Conversion
Morphological Analysis as Classification: an Inductive-Learning Approach.
Stretching the limits of learning without modules
Author(s): Antal van den Bosch and Ton Weijters
Reference: In M. van der Heyden, J. Mrsic-Flögel
and K. Weigl (Eds.), Proceedings of the HELNET International
Workshop on Neural Networks, Vol. I/II, Amsterdam: VU University
Press, pp. 177-185.
An inductive-learning approach to morphological analysis
Author(s): Antal van den Bosch, Walter Daelemans, and Ton
Weijters
Reference: In Durieux, G., Daelemans, W., and
Gillis, S. (Eds.), Papers from the Sixth Computational Linguistics
in the Netherlands Meeting, December 1996, University of Antwerp,
Belgium, pp. 213-230.
Avoiding overfitting in BP-SOM
Author(s): Ton Weijters, Antal van den Bosch, Eric Postma, and Jaap van den Herik
Reference: Avoiding overfitting in BP-SOM. In H.J. van den
Herik and A. Weijters (Eds.), Proceedings of BENELEARN-96,
Maastricht, pp. 157-166.
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
1995
The profit of learning exceptions
Scaling effects with greedy and lazy machine-learning
algorithms
Author(s): Antal van den Bosch, Ton Weijters, and Jaap van den Herik
Reference: In Proceedings of the Seventh Dutch Conference on
AI, NAIC-95, Erasmus University, Rotterdam, pp. 211-218.
Connectionism
Author(s): Ton Weijters and Antal van den Bosch
Reference: In Verschueren, J., Östman, J.O., and
Blommaert, J. (Eds.), Handbook of Pragmatics: Learning Manual,
pp. 165-171. Amsterdam: Benjamins.
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
1994
Measuring the complexity of writing systems
A language-independent, data-oriented architecture for grapheme-to-phoneme
conversion.
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
1993
Learnability and markedness: Dutch stress assignment
Author(s): Steven Gillis, Walter Daelemans, Gert Durieux and Antal
van den Bosch.
Reference: Proceedings of the Fifteenth Annual Conference
of the Cognitive Science Society, Boulder Colorado, USA, Hillsdale:
Lawrence Erlbaum Associates, 452-457, 1993.
-
[abs,
ps]
Tabtalk: Reusability in data-oriented grapheme-to-phoneme conversion.
Data-oriented methods for grapheme-to-phoneme conversion
Learnability and markedness in data-driven acquisition of stress
Author(s): Walter Daelemans, Steven Gillis, Gert Durieux and Antal
van den Bosch.
Reference: T. Mark Ellison and James M. Scobbie (eds) Computational
Phonology. Edinburgh Working Papers in Cognitive Science 8, 1993, 157-178.
-
[abs,
ps]
A data-driven approach to stress acquisition
Author(s): Walter Daelemans, Antal van den Bosch, Steven
Gillis, and Gert Durieux
Reference: In P. Adriaans (Ed.),
ECML-93 Workshop Notes on Machine Learning Techniques and Text
Analysis, Vienna, pp. 15-24.
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
1992
Generalization performance of backpropagation learning on a syllabification
task
Author(s): Walter Daelemans and Antal van den Bosch.
Reference: M.F.J. Drossaers and A. Nijholt (eds.) Connectionism
and Natural Language Processing. Proceedings Third Twente Workshop on Language
Technology, 27-38, 1992.
-
[abs,
ps]
A neural network for hyphenation
Author(s): Walter Daelemans and Antal van den Bosch
Reference: In: I. Aleksander and J. Taylor (Eds.), Artificial Neural Networks 2, Vol. 2. Amsterdam: North-Holland, pp. 1647-1650.
Linguistic pattern matching capabilities of connectionist networks
Author(s): Antal van den Bosch and Walter Daelemans
Reference: In: J. van Eijk and
W. Meyer Viol (Eds.), Proceedings of the Computational
Linguistics in the Netherlands meeting, CLIN-1991. Utrecht: OTS, pp. 40-53
(also appeared in W. Daelemans and D. Powers (Eds.), Proceedings
First SHOE Workshop, Tilburg: ITK, pp. 183-196.)
Exploring artificial learning algorithms: Learning to stress Dutch simplex words.
Author(s): Steven Gillis, Gert Durieux, Walter Daelemans, and Antal van den Bosch
Reference: Antwerp Papers in Linguistics 71.
|
|
|
|
|
|
|
| |
Last update: [an error occurred while processing this directive]
|
|
| |
