Abstract
Recently, neural network models with sequence labeling were adopted for Japanese predicate argument structure analysis (PASA). However, the sequence labeling approach can assign the same argument to multiple arguments. Thus, we propose a novel neural PASA method using pointer networks to alleviate the problem of multiple assignments. Experimental results show that our single model can achieve state-of-the-art performance on the NAIST Text Corpus without using syntactic features.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Japanese intra-sentential PASA includes intra-sentential zero anaphora; however, this and exophora are excluded here.
- 2.
Functional chunk.
- 3.
Dependency information was used only for evaluation.
- 4.
References
Akbik, A., Li, Y.: K-SRL: instance-based learning for semantic role labeling. In: Proceedings of COLING pp. 599–608 (2016)
Bergstra, J., Yamins, D., Cox, D.: Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures. In: Proceedings of ICML, pp. 115–123 (2013)
Cheng, P., Erk, K.: Implicit argument prediction as reading comprehension. arXiv preprint arXiv:1811.03554 (2018)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of EMNLP, pp. 1724–1734 (2014)
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493–2537 (2011)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL, pp. 4171–4186 (2019)
Faruqui, M., Dodge, J., Jauhar, S.K., Dyer, C., Hovy, E., Smith, N.A.: Retrofitting word vectors to semantic lexicons. In: Proceedings of NAACL. pp. 1606–1615 (2015)
FitzGerald, N., Täckström, O., Ganchev, K., Das, D.: Semantic role labeling with neural network factors. In: Proceedings of EMNLP, pp. 960–970 (2015)
Hacioglu, K.: Semantic role labeling using dependency trees. In: Proceedings of COLING, pp. 1273–1276 (2004)
Hayashibe, Y., Komachi, M., Matsumoto, Y.: Japanese predicate argument structure analysis exploiting argument position and type. In: Proceedings of IJCNLP, pp. 201–209 (2011)
He, L., Lee, K., Levy, O., Zettlemoyer, L.: Jointly predicting predicates and arguments in neural semantic role labeling. In: Proceedings of ACL, pp. 364–369 (2018)
Iida, R., Inui, K., Matsumoto, Y.: Exploiting syntactic patterns as clues in zero-anaphora resolution. In: Proceedings of ACL-COLING, pp. 625–632 (2006)
Imamura, K., Saito, K., Izumi, T.: Discriminative approach to predicate-argument structure analysis with zero-anaphora resolution. In: Proceedings of ACL-IJCNLP, pp. 85–88 (2009)
Li, J., Sun, A., Joty, S.: Segbot: a generic neural text segmentation model with pointer network. In: Proceedings of IJCAI, pp. 4166–4172 (2018)
Matsubayashi, Y., Inui, K.: Revisiting the design issues of local models for Japanese predicate-argument structure analysis. In: Proceedings of IJCNLP, pp. 128–133 (2017)
Matsubayashi, Y., Inui, K.: Distance-free modeling of multi-predicate interactions in end-to-end Japanese predicate argument structure analysis. In: Proceedings of COLING. pp. 94–106 (2018)
Omori, H., Komachi, M.: Multi-task learning for Japanese predicate argument structure analysis. In: Proceedings of NAACL, pp. 3404–3414 (2019)
Ouchi, H., Shindo, H., Duh, K., Matsumoto, Y.: Joint case argument identification for Japanese predicate argument structure analysis. In: Proceedings of ACL-IJCNLP, pp. 961–970 (2015)
Ouchi, H., Shindo, H., Matsumoto, Y.: Neural modeling of multi-predicate interactions for Japanese predicate argument structure analysis. In: Proceedings of ACL, pp. 1591–1600 (2017)
Pennington, J., Socher, R., Manning, C.: GloVe: Global vectors for word representation. In: Proceedings of HLT-EMNLP, pp. 1532–1543 (2014)
Peters, M.E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., Zettlemoyer, L.: Deep contextualized word representations. In: Proceedings of NAACL, pp. 2227–2237 (2018)
Pradhan, S., Hacioglu, K., Ward, W., Martin, J.H., Jurafsky, D.: Semantic role chunking combining complementary syntactic views. In: Proceedings of CoNLL, pp. 217–220 (2005)
Punyakanok, V., Roth, D., Yih, W.T.: The importance of syntactic parsing and inference in semantic role labeling. Computat. Linguistics 34(2), 257–287 (2008)
Strubell, E., Verga, P., Andor, D., Weiss, D., McCallum, A.: Linguistically-informed self-attention for semantic role labeling. In: Proceedings of EMNLP, pp. 5027–5038 (2018)
Taira, H., Fujita, S., Nagata, M.: A Japanese predicate argument structure analysis using decision lists. In: Proceedings of EMNLP, pp. 523–532 (2008)
Vaswani, A., et al.: Attention is all you need. In: Proceedings of NIPS, pp. 5998–6008 (2017)
Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Proceedings of NIPS, pp. 2692–2700 (2015)
Yoshikawa, K., Asahara, M., Matsumoto, Y.: Jointly extracting Japanese predicate-argument relation with Markov logic. In: Proceedings of IJCNLP, pp. 1125–1133 (2011)
Zhai, F., Potdar, S., Xiang, B., Zhou, B.: Neural models for sequence chunking. In: Proceedings of AAAI, pp. 3365–3371 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Takahashi, K., Omori, H., Komachi, M. (2020). Japanese Predicate Argument Structure Analysis with Pointer Networks. In: Nguyen, LM., Phan, XH., Hasida, K., Tojo, S. (eds) Computational Linguistics. PACLING 2019. Communications in Computer and Information Science, vol 1215. Springer, Singapore. https://doi.org/10.1007/978-981-15-6168-9_29
Download citation
DOI: https://doi.org/10.1007/978-981-15-6168-9_29
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-6167-2
Online ISBN: 978-981-15-6168-9
eBook Packages: Computer ScienceComputer Science (R0)