Skip to main content
Erschienen in:
Buchtitelbild

2016 | OriginalPaper | Buchkapitel

Improving Chinese Semantic Role Labeling with English Proposition Bank

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Most researches to SRL focus on English. It is still a challenge to improve the SRL performance of other language. In this paper, we introduce a two-pass approach to do Chinese SRL with a Recurrent Neural Network (RNN) model. We use English Proposition Bank (EPB) to improve the performance of Chinese SRL. Experimental result shows a significant improvement over the state-of-the-art methods on Chinese Proposition Bank (CPB), which reaches 78.39 % F1 score.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Fußnoten
1
Conditional clause is seen as a semantic role in the Chinese but not in the English.
 
2
PKU bilingual corpus is developed by Peking University, it is a English-Chinese parallel corpus. It contains 807,500 aligned English-Chinese sentence pairs and is available by licensing.
 
3
We use GIZA++ to get the translation probability from PKU bilingual corpus, GIZA++ can be download in http://​code.​google.​com/​p/​giza-pp/​downloads/​list.
 
Literatur
1.
Zurück zum Zitat Xue, N., Palmer, M.: Adding semantic roles to the Chinese Treebank. Nat. Lang. Eng. 15, 143–172 (2009)CrossRef Xue, N., Palmer, M.: Adding semantic roles to the Chinese Treebank. Nat. Lang. Eng. 15, 143–172 (2009)CrossRef
2.
Zurück zum Zitat Palmer, M., Gildea, D., Kingsbury, P.: The proposition bank: an annotated corpus of semantic roles. Comput. Linguist. J. 31, 71–106 (2005)CrossRef Palmer, M., Gildea, D., Kingsbury, P.: The proposition bank: an annotated corpus of semantic roles. Comput. Linguist. J. 31, 71–106 (2005)CrossRef
3.
Zurück zum Zitat Gildea, D., Jurafsky, D.: Automatic labeling of semantic roles. Comput. Linguist. 28, 245–288 (2002)CrossRef Gildea, D., Jurafsky, D.: Automatic labeling of semantic roles. Comput. Linguist. 28, 245–288 (2002)CrossRef
4.
Zurück zum Zitat Klementiev, A., Titov, I., Bhattarai, B.: Inducing crosslingual distributed representations of words. In: COLING (2012) Klementiev, A., Titov, I., Bhattarai, B.: Inducing crosslingual distributed representations of words. In: COLING (2012)
5.
Zurück zum Zitat Zou, W.Y., Socher, R., Cer, D., Manning, C.D.: Bilingual word embeddings for phrase-based machine translation. In: The 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1393–1398 (2013) Zou, W.Y., Socher, R., Cer, D., Manning, C.D.: Bilingual word embeddings for phrase-based machine translation. In: The 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1393–1398 (2013)
6.
Zurück zum Zitat Hermann, K.M., Blunsom, P.: Multilingual models for compositional distributed semantics. In: ACL, pp. 58–68 (2014) Hermann, K.M., Blunsom, P.: Multilingual models for compositional distributed semantics. In: ACL, pp. 58–68 (2014)
7.
Zurück zum Zitat Chandar, S., Lauly, S., Larochelle, H., Khapra, M.M., Ravindran, B., Raykar, V.C., Saha, A.: An autoencoder approach to learning bilingual word representations. In: NIPS, pp. 1853–1861 (2014) Chandar, S., Lauly, S., Larochelle, H., Khapra, M.M., Ravindran, B., Raykar, V.C., Saha, A.: An autoencoder approach to learning bilingual word representations. In: NIPS, pp. 1853–1861 (2014)
8.
Zurück zum Zitat Koomen, P., Punyakanok, V., Roth, D., Yih, W.T.: Generalized inference with multiple semantic role labeling systems. In: The Ninth Conference on Computational Natural Language Learning, pp. 181–184. Association for Computational Linguistics (2005) Koomen, P., Punyakanok, V., Roth, D., Yih, W.T.: Generalized inference with multiple semantic role labeling systems. In: The Ninth Conference on Computational Natural Language Learning, pp. 181–184. Association for Computational Linguistics (2005)
9.
Zurück zum Zitat Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: The 25th International Conference on Machine Learning, pp. 160–167. ACM (2008) Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: The 25th International Conference on Machine Learning, pp. 160–167. ACM (2008)
10.
Zurück zum Zitat Xue, N., Palmer, M.: Automatic semantic role labeling for Chinese verbs. In: IJCAI, vol. 5, pp. 1160–1165. Citeseer (2005) Xue, N., Palmer, M.: Automatic semantic role labeling for Chinese verbs. In: IJCAI, vol. 5, pp. 1160–1165. Citeseer (2005)
12.
Zurück zum Zitat Sun, W.: Semantics-driven shallow parsing for Chinese semantic role labeling. In: ACL, pp. 103–108 (2010) Sun, W.: Semantics-driven shallow parsing for Chinese semantic role labeling. In: ACL, pp. 103–108 (2010)
13.
Zurück zum Zitat Yang, H., Zong, C.: Multipredicate semantic role labeling. In: The 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 363–373 (2014) Yang, H., Zong, C.: Multipredicate semantic role labeling. In: The 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 363–373 (2014)
14.
Zurück zum Zitat Wang, Z., Jiang, T., Chang, B., Sui, Z.: Chinese semantic role labeling with bidirectional recurrent neural networks. In: The 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1626–1631 (2015) Wang, Z., Jiang, T., Chang, B., Sui, Z.: Chinese semantic role labeling with bidirectional recurrent neural networks. In: The 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1626–1631 (2015)
15.
Zurück zum Zitat Li, T., Chang, B.: Semantic role labeling using recursive neural network. In: Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data, pp. 66–76 (2015) Li, T., Chang, B.: Semantic role labeling using recursive neural network. In: Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data, pp. 66–76 (2015)
Metadaten
Titel
Improving Chinese Semantic Role Labeling with English Proposition Bank
verfasst von
Tianshi Li
Qi Li
BaoBao Chang
Copyright-Jahr
2016
DOI
https://doi.org/10.1007/978-3-319-47674-2_1