Domain Adaptation in Semantic Role Labeling Using a Neural Language Model and Linguistic Resources

IEEE/ACM Transactions on Audio Speech and Language Processing

Volumn 23, Issue 11, 2015, Pages 1812-1823

  Do, Quynh Thi Ngoc ^a   Bethard, Steven ^b   Moens, Marie Francine ^a  

^a UNIVERSITY OF LEUVEN   (Belgium)

^b UNIVERSITY OF ALABAMA AT BIRMINGHAM   (United States)

Author keywords

Language model; linguistic resources; open domain; semantic role labeling

Indexed keywords

LINGUISTICS; RECURRENT NEURAL NETWORKS; SEMANTICS;

DOMAIN ADAPTATION; LANGUAGE MODEL; LINGUISTIC RESOURCES; LUND UNIVERSITY; OPEN DOMAIN; PART OF SPEECH; SEMANTIC ROLE LABELING; TRAINING EXAMPLE;

COMPUTATIONAL LINGUISTICS;

EID: 84937397322     PISSN: 23299290     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASLP.2015.2449072     Document Type: Article

References (35)

1. M. Palmer , D. Gildea, and N. Xue, Semantic Role Labeling, ser. ser. Synthesis Lectures on Human Language Technologies. San Rafael, CA, USA: Morgan & Claypool, 2010.
2. K. Deschacht and M.-F. Moens, "Semi-su pervised semantic role labeling using the latent words language model," in Proc. Conf. Empir. Meth. Nat. Lang. Process. (EMNLP'09), 2009, pp. 21-29, ACL.
3. F. Huang, A. Ahuja, D. Downey, Y. Yang, Y. Guo, and A. Yates, " Learning representations for weakly supervised natural language processing tasks," Comput. Linguist., vol. 40, pp. 85-120, 2013.
4. M. Baroni, G. Dinu, and G. Kruszewski, " Don't count, predict! a systematic comparison of context-counting vs. context-predicting semantic vectors," in Proc. 52nd Annu. Meeting Assoc. Comput. Linguist. (Vol. 1: Long Papers), Baltimore, MD, USA, Jun. 2014, pp. 238-247 [Online]. Available: http://www.aclweb.org/anthology/P14-1023, ACL
5. J. Weston, F. Ratle, and R. Collobert, "Deep learning via semi-supervised embedding, " in Proc. 25th Int. Conf. Mach. Learn., New York, NY, USA, 2008, pp. 1168-1175 [Online]. Available: http://doi.acm. org/10.1145/1390156.1390303, ser. ICML'08, ACM
6. R. Collobert, "Deep learning for efficient discriminative parsing, " in Proc . AISTATS, 2011.
7. W. De Mulder, S. Bethard, and M.-F. Moens, " A survey on the application of recurrent neural networks to statistical language modeling," Comput. Speech Lang., vol. 30, no. 1, pp. 61-98, 2015 [Online]. Available: https://lirias.kuleuven.be/handle/123456789/462643
8. T. Mikolov, K. Chen, G. Corrado, and J. Dean, "Efficient estimation of word representations in vector space, " arXiv preprint arXiv:1301.3781, 2013.
9. K. Deschacht, J. De Belder, and M.-F. Moens, "The latent words language model, " Comput. Speech Lang., vol. 26, no. 5, pp. 384-409, Oct. 20 12 [Online]. Available: https://lirias.kuleuven.be/handle/123456789/344914
10. K. M. Hermann, D. Das, J. Weston, and K. Ganchev, " Semantic frame identification with distributed word representations," in Proc. 52th Annu. Meeting Assoc. Comput. Linguist., 2014.
11. H. Fürstenau and M. Lapata, "Semi-supervised semantic role labeling via structural alignment, " Comput. Linguist., vol. 38, no. 1, pp . 135-171, Mar. 2012 [Online]. Available: http://dx.doi.org/10.1162/COLI-A-00087
12. O. Kolomiyets, S. Bethard, and M.-F. Moens, "Model-portability experiments for textual temporal analysis, " in Proc. 49th Ann u. Meeting Assoc. Comput. Linguist.: Human Lang. Technol., Stroudsburg, PA, USA, 2011, pp. 271-276 [Online]. Available: http://dl.acm.org/citation. cfm?id=2002736.2002793, ser. HLT'11, ACL
13. D. McClosky, E. Charniak, and M. Johnson, " Effective self-training for parsing," in Proc. Main Conf. Human Lang. Technol. Conf. North Amer. Chap. Assoc. of Comput. Linguist., Stroudsburg, PA, USA, 2006, pp. 152-159 [Online]. Available: http://dx.doi.org/10.3115/1220835. 1220855, ser. HLT-NAACL '06, ACL
14. Y. Si, Z. Zhang, T. Li, J. Pan, and Y. Yan, " Enhanced word classing for recurrent neural network language model," JICS: J. Inf. Comput. Sci., Vol. 10, pp. 3595-3604, 2013.
15. R. Samad Zadeh Kaljahi, "Adapting self-training for semantic role labeling, " in Proc. ACL 2010 Student Research Workshop, 2010, pp. 91-96 [Online]. Available: http://aclweb.org/anthology/P10-3016, ACL
16. J. Naradowsky, S. Riedel, and D. A. Smith, "Improving nlp through marginalization of hidden syntactic structure, " in Proc. Conf. Empir. Meth, i n Nat. Lang. Process. (EMNLP '12), Jeju, Korea, Jul. 2012, ACL.
17. M. Gormley, M. Mitchell, B. Van Durme, and M. Dredze, " Low-resource semantic role labeling," in Assoc. for Comput. Linguist. (ACL), Jun. 2014 [Online]. Available: http://www.cs.jhu.edu/mrg/publications/srl-Acl-2014.pdf
18. R. S. Swier and S. Stevenson, "Unsupervised semantic role labelling, " in Proc. Conf. Empir. Meth. Nat. Lang. Process. (EMNLP'04), 2004, pp. 95-102, ACL.
19. O. Abend, R. Reichart, and A. Rappoport, "Unsupervised argument identification for semantic role labeling, " in Proc. Joint Conf. 47th Annu. Meeting ACL and 4th Int. Joint Conf. Nat. Lang. Process. AFNLP: Vol. 1, Stroudsburg, PA, USA, 2009, pp. 28-36 [Online]. Available: http://dl.acm.org/citation.cfm?id=1687878.1687884, ser. ACL '09, ACL
20. T. Grenager and C. D. Manning, "Unsupervised discovery of a statistical verb lexicon, " in Proc. Conf. Empir. Meth. Nat. Lang. Process. (EMNLP'06), D. Jurafsky and E. Gaussier, Eds., 2006, pp. 1-8, ACL.
21. M. Baroni and A. Lenci, "Distributional Memory: A general framework for corpus-based semantics, " Comput. Linguist., vol. 36, no. 4, pp. 673-721, 2010.
22. P. D. Turney and P. Pantel, "From frequency to meaning: Vector space models of semantics, " J. Artif. Int. Res., vol. 37, no. 1, pp. 141-188, Jan. 2010 [Online]. Available: http://dl.acm.org/citation.cfm?id=1861751. 1861756
23. P. F. Brown, P. V. deSouza, R. L. Mercer, V. J. D. Pietra, and J. C. Lai, " Class-based n-gram models of natural language," Comput. Linguist., vol. 18, no. 4, pp. 467-479, Dec. 1992 [Online]. Availa ble: http://dl. acm.org/citation.cfm?id=176313.176316
24. P. Liang, "Semi-supervised learning for natural language, " M.S. thesis, Mass. Inst. of Technol., Cambridge, MA, USA, 2005.
25. M. Palmer,P. Kingsbury,D. Gildea The proposition bank: An annotated corpus of semantic roles Comput. Linguist. 31, 1, 71-106, 2005
26. A. Meyers, R. Reeves, C. Macleod, R. Szekely, V. Zielinska, B. Young, and R. Grishman, " The nombank project: An interim report," in Proc. HLT-NAACL 2004Workshop: Frontiers in Corpus Annotation, A. Meyers, Ed., Boston, MA, USA, May 2-7, 2004, pp. 24-31, ACL.
27. K. K. Schuler, "Verbnet: A broad-coverage, comprehensive verb lexicon, " Ph.D. dissertation, Univ. of Pennsylvania, Philadelphia, PA, USA, 2006 [Online]. Available: http://verbs.colorado.edu/kipper/Papers/dissertation.pdf
28. B. Levin, English Verb Classes and Alternations A Preliminary Investigation. Chicago, IL, USA: Univ. of Chicago Press, 1993.
29. G. A. Miller, " WordNet: A lexical database for English," Commun. ACM, vol. 38, no. 11, pp. 39-41, Nov. 1995 [Online]. Available: http://doi.acm.org/10.1145/219717.219748
30. A. Björkelund, L. Hafdell, and P. Nugues, " Multilingual semantic role labeling," in Proc. 13th Conf. Comput. Nat. Lang. Learn.: Shared Task, Stroudsburg, PA, USA, 2009, pp. 43-48 [Online]. Available: http://dl. acm.org/citation.cfm?id=1596409.1596416, ser. CoNLL '09, ACL
31. R.-E. Fan, K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin, " LIBLINEAR: A library for large linear classification," J. Mach. Learn. Res., vol. 9, pp. 1871-1874, 2008.
32. T. Mikolov, M. Karafi át, L. Burget, J. Cernocký, and S. Khudanpur, " Recurrent neural network based language model," in Proc. Interspeech, T. Kobayashi, K. Hirose, and S. Nakamura, Eds., 2010, pp. 1045-1048, ISCA.
33. A. Taylor, M. Marcus, and B. Santorini, "The Penn Treebank: An Overview, " in Treebanks, A. Abeillé , Ed. New York, NY, USA: Springer, 2003, pp. 5-22.
34. T. Mikolov, "Statistical language models based on neural networks," Ph.D. dissertation, Brno Univ. of Technology, Brno, Czech Republic, 2012.
35. , O. Chapelle, B. Scholkopf, and A. Zien, Eds., Semi-Supervised Learning. Cambridge, MA, USA: MIT Press, 2006.