Browse > Article
http://dx.doi.org/10.4218/etrij.14.0113.0645

Domain-Adaptation Technique for Semantic Role Labeling with Structural Learning  

Lim, Soojong (SW.Content Research Laboratory, ETRI)
Lee, Changki (Department of Computer Science, Kangwon National University)
Ryu, Pum-Mo (SW.Content Research Laboratory, ETRI)
Kim, Hyunki (SW.Content Research Laboratory, ETRI)
Park, Sang Kyu (SW.Content Research Laboratory, ETRI)
Ra, Dongyul (Division of Computer &Telecommunication Engineering, Yonsei University)
Publication Information
ETRI Journal / v.36, no.3, 2014 , pp. 429-438 More about this Journal
Abstract
Semantic role labeling (SRL) is a task in natural-language processing with the aim of detecting predicates in the text, choosing their correct senses, identifying their associated arguments, and predicting the semantic roles of the arguments. Developing a high-performance SRL system for a domain requires manually annotated training data of large size in the same domain. However, such SRL training data of sufficient size is available only for a few domains. Constructing SRL training data for a new domain is very expensive. Therefore, domain adaptation in SRL can be regarded as an important problem. In this paper, we show that domain adaptation for SRL systems can achieve state-of-the-art performance when based on structural learning and exploiting a prior model approach. We provide experimental results with three different target domains showing that our method is effective even if training data of small size is available for the target domains. According to experimentations, our proposed method outperforms those of other research works by about 2% to 5% in F-score.
Keywords
Domain adaptation; semantic role labeling; natural language; semantic analysis; structured learning; prior model;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 C. Lee and M. Jang, "A Modified Fixed-Threshold SMO for 1-Slack Structural SVMs," ETRI J., vol. 32, no. 1, Feb. 2010, pp. 120-128.   DOI   ScienceOn
2 C. Cortes and V. Vapnik, "Support-Vector Networks," Mach. Learning, vol. 20, no. 3, Sept. 1995, pp. 273-297.
3 S. Shalev-Shwartz et al., "Pegasos: Primal Estimated Sub-Gradient Solver for SVM," Proc. ICML, Corvallis, Oregon, USA, June 20-24, 2007, pp. 807-814.
4 I. Tsochantaridis et al., "Support Vector Machine Learning for Interdependent and Structured Output Space," Proc. ICML, July 2004.
5 J. Kim et al., "GENIA Corpus-a Semantically Annotated Corpus for Bio-textmining," Bioinformat., vol. 19, no. 1, July 2003, pp. i180-i182.   DOI   ScienceOn
6 D. Dahlmeier and H.T. Ng, "Domain Adaptation for Semantic Role Labeling in the Biomedical Domain," Bioinformat., vol. 26, no. 8, Apr. 2010, pp. 1098-1104.   DOI   ScienceOn
7 R. Tsai et al., "BIOSMILE: A Semantic Role Labeling System for Biomedical Verbs Using a Maximum-Entropy Model with Automatically Generated Template Features," BMC Bioinformat., vol. 8, no. 325, Sept. 2007.
8 H-J. Oh, C.K. Lee, and C-H. Lee, "Analysis of the Empirical Effects of Contextual Matching Advertising for Online News," ETRI J., vol. 34, no. 2, Apr. 2012, pp. 292-295.   DOI
9 X. Carreras and L. Marquez, "Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling," Proc. CoNLL, Ann Arbor, Michigan, USA, June 30, 2005, pp. 152-154.
10 S. Pradhan, W. Ward, and J. Martin, "Towards Robust Semantic Role Labeling," Computational Linguistics, vol. 34, no. 2, June 2008, pp. 289-310.   DOI   ScienceOn
11 M. Surdeanu et al., "The CoNLL-2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies," Proc. CoNLL, Manchester, UK, Aug. 2008, pp. 159-177.
12 J. Hajic et al., "The CoNLL-2009 Shared Task: Syntactic and Semantic Dependencies in Multiple Languages," Proc. CoNLL, Boulder, CO, USA, June 2009, pp. 1-18.
13 S. Lim, C. Lee, and D. Ra, "Dependency-Based Semantic Role Labeling Using Sequence Labeling with a Structural SVM," Pattern Recogn. Lett., vol. 34, no. 6, Apr. 2013, pp. 696-702.   DOI   ScienceOn
14 C. Chelba and A. Acero, "Adaptation of Maximum Entropy Capitalizer: Little Data Can Help a Lot," Comput. Speech Language, vol. 20, no. 4, Oct. 2006, pp. 382-399.   DOI   ScienceOn
15 H. Daume, "Frustratingly Easy Domain Adaptation," Proc. ACL, Prague, Czech, June 2007, pp. 256-263.
16 J. Jiang and C. Zhai, "Instance Weighting for Domain Adaptation in NLP," Proc. ACL, Prague, Czech, June 2007, pp. 264-271.
17 J.R. Finkel and C.D. Manning, "Hierarchical Bayesian Domain Adaptation," Proc. NAACL, Boulder, CO, USA, May 2009, pp. 602-610.
18 J. Blitzer, R. McDonald, and F. Pereira, "Domain Adaptation with Structural Correspondence Learning," Proc. EMNLP, Sydney, Australia, July 22-23, 2006, pp. 120-128.
19 F. Huang and A. Yates, "Distributional Representations for Handling Sparsity in Supervised Sequence-Labeling," Proc. IJCNLP AFNLP, Singapore, vol. 1, Aug. 2-7, 2009, pp. 495-503.
20 H. Daume and D. Marcu, "Domain Adaptation for Statistical Classifiers," J. Artif. Intell. Res., vol. 26, no. 1, May 2006, pp. 101-126.
21 M. Surdeanu et al., "Using Predicate-Argument Structures for Information Extraction," Proc. ACL, vol. 1, July 2003, pp. 8-15.
22 C. Lee and M. Jang, "A Prior Model of Structural SVMs for Domain Adaptation," ETRI J., vol. 33, no. 5, Oct. 2011, pp. 712-719.   DOI