Elamur Research⌕
☰
home / papers / 2008 / Labeling Chinese Predicates with Semantic Roles

Labeling Chinese Predicates with Semantic Roles

Summary

This article addresses semantic role labeling (SRL) for Chinese, which had seen little research because no large annotated corpus was available. Xue builds the first Chinese SRL system trained and evaluated on two sizable resources layered over the Chinese Treebank. The Chinese PropBank covers verbs, and the Chinese NomBank covers nominalized predicates. Both use the English PropBank scheme: predicate-specific core roles (Arg0–Arg5) plus ArgM modifier tags. A Maximum Entropy classifier, using features taken from English SRL work, is tested on four kinds of input trees. These are gold treebank parses, automatic parses with gold segmentation and POS tags, automatic parses with gold segmentation only, and fully automatic parses. With gold trees, accuracy on verbs matches the English state of the art, although the training data is much smaller. Performance declines as more preprocessing is automated, and nominalized predicates are consistently harder than verbs. The study shows that standard SRL features transfer well between languages. It identifies Chinese parsing, including segmentation and tagging, as the main obstacle to practical systems.

Key points

  • Resources: Chinese PropBank (Xue and Palmer 2003) and Chinese NomBank (Xue 2006a) assign role labels to constituents in the Chinese Treebank, released by Xue et al. (2005). That treebank is only about half the size of the Penn Treebank.
  • Setup: A Maximum Entropy learner (McCallum 2002) is evaluated on gold parses and on three levels of automatic parsing. This isolates how much segmentation, POS tagging and parsing each contribute to errors.
  • Why gold-parse verb results are strong: The author points to lower verb polysemy in Chinese and the many stative verbs with simple argument structures. A further reason is that the treebank structurally separates arguments from adjuncts.
  • Why nominalizations are harder: NPs in the treebank are flatter and lack a clear argument/adjunct split. Their arguments may also sit inside the NP, outside it, or in modifying relative clauses.
  • Context: Earlier Chinese work was small-scale. Sun and Jurafsky (2004) studied 10 verbs. Kwong and T'sou (2005) labeled argument heads for 41 verbs, reaching F1 0.529 on textbook data and 0.444 on news. For comparison, English SRL with automatic parses reached about 0.81 F on Penn Treebank Section 23.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Natural language processing

Topics: Semantic role labeling

Institutions

🎓University of Colorado BoulderBoulder · United States41 works · 48 832 citations

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli.2008.34.2.225

@article{xue2008labeling,
  title = {{Labeling Chinese Predicates with Semantic Roles}},
  author = {Xue, Nianwen},
  journal = {Computational Linguistics},
  year = {2008},
  doi = {10.1162/coli.2008.34.2.225},
  url = {https://doi.org/10.1162/coli.2008.34.2.225}
}

References

64 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Baker, Collin F., Charles J. Fillmore, and John B. Lowe. 1998. The Berkeley FrameNet project. In Proceedings of COLING/ACL, pages 86–90, Montreal, Canada. find our card
  2. Baldewein, Ulrike, Katrin Erk, Sebastian Padó, and Detlef Prescher. 2004. Semantic role labelling with similarity-based generalization using em-based clustering. In Rada Mihalcea and Phil Edmonds, editors, Proceedings of Senseval-3, pages 64–68, Barcelona, Spain. find
  3. Bejan, Cosmin Adrian, Alessandro Moschitti, Paul Morărescu, Gabriel Nicolae, and Sanda Harabagiu. 2004. Semantic parsing based on framenet. In Rada Mihalcea and Phil Edmonds, editors, Proceedings of Senseval-3, pages 73–76, Barcelona, Spain. find
  4. Bender, Emily. 2000. The syntax of Mandarin -ba. Journal of East Asian Linguistics, 9(2):105–145. find
  5. Bikel, Daniel M. 2004. On the Parameter Space of Generative Lexicalized Statistical Parsing Models. Ph.D. thesis, University of Pennsylvania. find
  6. Boas, Hans C. 2002. Bilingual FrameNet dictionaries for machine translation. In Proceedings of LREC 2002, pages 1364–1371, Las Palmas, Spain. find our card
  7. Burchardt, A., K. Erk, A. Frank, A. Kowalski, S. Pado, and M. Pinkal. 2006. The SALSA Corpus: a German corpus resource for lexical semantics. In Proceedings of LREC 2006, pages 969–974, Genoa, Italy. find our card
  8. Carreras, Xavier and Lluı́s Màrquez. 2004a. Hierarchical recognition of propositional arguments with perceptrons. In Proceedings of the Eighth Conference on Natural Language Learning, pages 106–109, Boston, MA. find
  9. Carreras, Xavier and Lluı́s Màrquez. 2004b. Introduction to the CoNLL-2004 shared task: Semantic role labeling. In Proceedings of the Eighth Conference on Natural Language Learning, pages 89–97, Boston, MA. find
  10. Carreras, Xavier and Lluı́s Màrquez. 2005. Introduction to the CoNLL-2005 shared task: Semantic role labeling. In Proceedings of the Nineth Conference on Natural Language Learning, pages 152–164, Ann Arbor, MI. find our card
  11. Chen, Ying, Hongling Sun, and Dan Jurafsky. 2005. A corrigendum to Sun and Jurafsky (2004) ”Shallow Semantic Parsing of Chinese.” Technical Report TR-CSLR-2005-01, University of Colorado at Boulder CSLR Tech Report. find
  12. Cohn, Trevor and Philip Blunsom. 2005. Semantic role labeling with tree conditional random fields. In Proceedings of CoNLL2005, pages 169–172, Ann Arbor, MI. find
  13. Collins, Michael. 1999. Head-driven Statistical Models for Natural Language Parsing. Ph.D. thesis, University of Pennsylvania. find
  14. Erk, K. and S Padó. 2005. Analyzing models for semantic role assignment using confusability. In Proceedings of HLT-EMNLP, pages 891–898, Vancouver, British Columbia, Canada. find
  15. Gabbard, Ryan, Seth Kulick, and Mitchell Marcus. 2006. Fully parsing the Penn treebank. In Proceedings of HLT-NAACL 2006, pages 184–191, New York, NY. find our card
  16. Gildea, D. and D. Jurafsky. 2002. Automatic labeling for semantic roles. Computational Linguistics, 28(3):245–288. find
  17. Girju, Roxana, Ana-Maria Giuglea, Marian Olteanu, Ovidiu Fortu, Orest Bolohan, and Dan Moldovan. 2004. Support vector machines applied to the classification of semantic relations. In Proceedings of the HLT/NAACL Workshop on Computational Lexical Semantics, pages 68–75, Boston, MA. find
  18. Hacioglu, Kadri, Sameer Pradhan, Wayne Ward, James H. Martin, and Daniel Jurafsky. 2004. Semantic role labeling by tagging syntactic chunks. In Proceedings of CoNLL-2004, pages 110–113, Ann Arbor, MI. find
  19. Haghighi, Aria, Kristina Toutanova, and Christopher Manning. 2005. A joint model for semantic role labeling. In Proceedings of CoNLL, pages 173–176, Ann Arbor, MI. find
  20. Huang, James C. T. 1999. Chinese passives in comparative perspective. Tsing Hua Journal of Chinese Studies, 29:423–509. find
  21. Jiang, Zheng Ping and Hwee Tou Ng. 2006. Semantic role labeling of NomBank: A maximum entropy approach. In Proceedings of the EMNLP, pages 138–145, Sydney, Australia. find
  22. Kipper, K., A. Korhonen, N. Bryant, and M. Palmer. 2006. Extending verbNet with novel verb classes. In Proceedings of LREC, Genoa, Italy. find
  23. Koomen, Peter, Vasin Punyakanok, Dan Roth, and Wen tau Yih. 2005. Generalized inference with multiple semantic role labeling systems. In Proceedings of the Nineth Conference on Natural Language Learning, pages 181–184, Ann Arbor, MI. find
  24. Kwon, Namhee, Michael Fleischman, and Eduard Hovy. 2004. Senseval automatic labeling of semantic roles using Maximum Entropy models. In Rada Mihalcea and Phil Edmonds, editors, Proceedings of Senseval-3, pages 129–132, Barcelona, Spain. find
  25. Kwong, Oi Yee and Benjamin K. T’sou. 2005. Data homogeneity and semantic role tagging in Chinese. In Proceedings of the ACL-SIGLEX Workshop on Deep Lexical Acquisition, pages 1–9, Ann Arbor, MI. find
  26. Lapata, Maria. 2002. The disambiguation of nominalizations. Computational Linguistics, 28(3):357–388. find
  27. Levi, Judith. 1979. The Syntax and Semantic of Complex Nominals. New York: Academic Press. find
  28. Levin, Beth. 1993. English Verbs and Alternations: A Preliminary Investigation. Chicago: The Unversity of Chicago Press. find
  29. Litkowski, Ken. 2004. Senseval-3 task: Automatic labeling of semantic roles. In Rada Mihalcea and Phil Edmonds, editors, Proceedings of Senseval-3, pages 9–12, Barcelona, Spain. find
  30. Liu, T., W. Che, S. Li, Y. Hu, and H. Liu. 2005. Semantic role labeling with a maximum entropy classifier. In Proceedings of CoNLL-2005, pages 189–192, Ann Arbor, MI. find
  31. Luo, Xiaoqiang. 2003. A maximum entropy Chinese character-based parser. In Proceedings of EMNLP, Sapporo, Japan. find
  32. Marcus, Mitchell P., Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19(2):313–330. find our card
  33. Màrquez, Lluı́s, Mihai Surdeanu, Pere Comas, and Jordi Turmo. 2005. A robust combination strategy for semantic role labeling. In Proceedings of HLT/EMNLP 2005, pages 644–651, Vancouver, Canada. find
  34. McCallum, Andrew Kachites. 2002. Mallet: A machine learning for language toolkit. Available at http://mallet.cs.umass.edu. ↗
  35. Melli, G., Y. Wang, Y. Liu, M. M. Kashani, Z. Shi, B. Gu, A. Sarkar, and F. Popowich. 2005. Description of SQUASH, the SFU question and summary handler for the DUC-2005 summarization task. In Document Understanding Conference 2005, Vancouver, Canada. find
  36. Meyers, A., R. Reeves, C. Macleod, R. Szekely, V. Zielinska, B. Young, and R. Grishman. 2004. The NomBank Project: An interim report. In Proceedings of the NAACL/HLT Workshop on Frontiers in Corpus Annotation, pages 24–31, Boston, MA. find our card
  37. Meyers, A., R. Reeves, and Catherine Macleod. 2004. NP-External arguments: A study of argument sharing in English. In The ACL 2004 Workshop on Multiword Expressions: Integrating Processing, pages 96–103, Barcelona, Spain. find
  38. Moldovan, Dan and Adriana Badulescu. 2005. A semantic scattering model for the automatic interpretation of genitives. In Proceedings of HLT-EMNLP, pages 891–898, Vancouver, Canada. find
  39. Moldovan, Dan, Roxana Girju, Marian Olteanu, and Ovidiu Fortu. 2004. SVM classification of FrameNet semantic roles. In Proceedings of Senseval-3, pages 167–170, Barcelona, Spain. find
  40. Nakov, Preslav and Marti Hearst. 2006. Using verbs to characterize noun-noun relations. In Proceedings of AIMSA, pages 233–244, Varna, Bulgaria. find
  41. Narayanan, Srini and Sanda Harabagiu. 2004. Question answering based on semantic structures. In Proceedings of the 20th International Conference on Computational Linguistics, pages 693–701, Geneva, Switzerland. find
  42. Ngai, Grace, Dekai Wu, Marine Carpuat, Chi-Shing Wang, and Chi-Yung Wang. 2004. Semantic role labeling with boosting, svms, maximum entropy, snow, and decision lists. In Rada Mihalcea and Phil Edmonds, editors, Proceedings of Senseval-3, pages 183–186, Barcelona, Spain. find
  43. Palmer, Martha, Daniel Gildea, and Paul Kingsbury. 2005. The Proposition Bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–106. find our card
  44. Pradhan, Sameer, Kadri Hacioglu, Wayne Ward and James H. Martin, and Daniel Jurafsky. 2005. Semantic role chunking combining complementary syntactic views. In Proceedings of CoNLL 2005, pages 217–220, Ann Arbor, MI. find
  45. Pradhan, Sameer, Kadri Hacioglu, Wayne Ward, James H. Martin, and Daniel Jurafsky. 2003. Semantic role parsing: Adding semantic structure to unstructured text. In Proceedings of the International Conference on Data Mining (ICDM-2003), pages 629–632, Melbourne, FL. find
  46. Pradhan, Sameer, Honglin Sun, Wayne Ward, James H. Martin, and Daniel Jurafsky. 2004. Parsing arguments of nominalizations in English and Chinese. In Proceedings of NAACL-HLT 2004, pages 141–144, Boston, MA. find
  47. Pradhan, Sameer, Wayne Ward, Kadri Hacioglu, James H. Martin, and Dan Jurafsky. 2005. Semantic role labeling using different syntactic views. In Proceedings of ACL 2005, pages 581–588, Ann Arbor, MI. find
  48. Pradhan, Sameer, Wayne Ward, Kadri Hacioglu, James H. Martin, and Daniel Jurafsky. 2004. Shallow semantic parsing using support vector machines. In Proceedings of NAACL-HLT 2004, pages 233–240, Boston, MA. find our card
  49. Punyakanok, Vasin, Dan Roth, and W. Yih. 2005. The necessity of syntactic parsing for semantic role labeling. In Proceedings of IJCAI-2005, pages 1124–1129, Edinburgh, UK. find
  50. Punyakanok, Vasin, Dan Roth, Wen Tau. Yih, and Dav Zimak. 2004. Semantic role labeling via integer programming inference. In Proceedings of COLING-2004, pages 1346–1352, Geneva, Switzerland. find
  51. Sgall, Petr, Jarmila Panevová, and Eva Hajičová. 2004. Deep syntactic annotation: Tectogrammatical representation and beyond. In A. Meyers, editor, Proceedings of the HLT-NAACL 2004 Workshop: Frontiers in Corpus Annotation, pages 32–38, Boston, MA. find
  52. Sun, Honglin and Daniel Jurafsky. 2004. Shallow semantic parsing of Chinese. In Proceedings of NAACL 2004, pages 249–256, Boston, MA. find
  53. Surdeanu, Mihai, Sanda Harabagiu, John Williams, and Paul Aarseth. 2005. Using predicate-argument structures for information extraction. In Proceedings of ACL 2003, Ann Arbor, MI. find our card
  54. Thompson, Cynthia, Siddharth Patwardhan, and Carolin Arnold. 2004. Generative models for semantic role labeling. In Rada Mihalcea and Phil Edmonds, editors, Proceedings of Senseval-3, pages 235–238, Barcelona, Spain. find
  55. Toutanova, Kristina, Aria Haghighi, and Christopher Manning. 2005. Joint learning improves semantic role labeling. In Proceedings of ACL-2005, pages 589–596, Ann Arbor, MI. find our card
  56. Tsai, Tzong-Han, Chia-Wei Wu, Yu-Chun Lin, and Wen lian Hsu. 2005. Exploiting full parsing information to label semantic roles using an ensemble of ME and SVM via integer linear programming. In Proceedings of CoNLL-2005, pages 233–236, Ann Arbor, MI. find
  57. Xue, Nianwen. 2006a. Annotating the predicate-argument structure of Chinese nominalizations. In Proceedings of the Fifth International Conference on Language Resources and Evaluation, pages 1382–1387, Genoa, Italy. find
  58. Xue, Nianwen. 2006b. Semantic role labeling of nominalized predicates in Chinese. In Proceedings of HLT-NAACL 2006, pages 431–438, New York, NY. find
  59. Xue, Nianwen and Martha Palmer. 2003. Annotating the propositions in the Penn Chinese Treebank. In The Proceedings of the 2nd SIGHAN Workshop on Chinese Language Processing, Sapporo, Japan. find
  60. Xue, Nianwen and Martha Palmer. 2004. Calibrating features for semantic role labeling. In Proceedings of 2004 Conference on Empirical Methods in Natural Language Processing, pages 88–94, Barcelona, Spain. find
  61. Xue, Nianwen and Martha Palmer. 2005. Automatic semantic role labeling for Chinese verbs. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, pages 1160–1165, Edinburgh, Scotland. find
  62. Xue, Nianwen, Fei Xia, Fu dong Chiou, and Martha Palmer. 2005. The Penn Chinese TreeBank: Phrase structure annotation of a large corpus. Natural Language Engineering, 11(2):207–238. find
  63. Yi, Szuting, Edward Loper, and Martha Palmer. 2007. Can semantic roles generalize across genres? In Proceedings of NAACL-2007, pages 548–555, Rochester, NY. find
  64. Yi, Szuting and Martha Palmer. 2005. The integration of syntactic parsing and semantic role labeling. In Proceedings of CoNLL-2005, pages 237–240, Ann Arbor, MI. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/xue-2008-labeling-chinese-predicates-semantic-roles/