Abstract
Semantic Role Labeling is the task of automatically detecting the semantic role played by words or phrases in a sentence. There is a small number of studies dedicated to Semantic Role Labeling in the Portuguese language, and the obtained performance is far from that of the English language. In this article, we propose an end-to-end semantic role labeler for the Portuguese language, which leans on a deep bidirectional long short-term memory neural network architecture. The predictions are used as inputs to an inference stage that employs a global recursive neural parsing algorithm, tailored for the task. We also provide a detailed analysis of the effects of word embedding dimensionality and network depth on the overall performance of the proposed model. The proposed approach outperforms the state-of-the-art approach on the PropBank-Br corpus, while reducing the relative error in approximately 8.74%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Available at http://nilc.icmc.usp.br/nlpnet/.
- 2.
The source code is available at https://github.com/dfalci/deep_pt_srl.
- 3.
Sequences of numbers were transformed into the ‘#’ token while email addresses and URLs were replaced by the ‘@’ token.
- 4.
The training time varies according to the dimensionality.
References
Alva-Manchego, F.E., Rosa, J.L.G.: Towards semi-supervised brazilian portuguese semantic role labeling: building a benchmark. In: Caseli, H., Villavicencio, A., Teixeira, A., Perdigão, F. (eds.) PROPOR 2012. LNCS (LNAI), vol. 7243, pp. 210–217. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-28885-2_24
Alva-Manchego, F.E., Rosa, J.L.G.: Semantic role labeling for Brazilian Portuguese: a benchmark. In: Pavón, J., Duque-Méndez, N.D., Fuentes-Fernández, R. (eds.) IBERAMIA 2012. LNCS (LNAI), vol. 7637, pp. 481–490. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-34654-5_49
Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)
Bird, S., Klein, E., Loper, E.: Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. O’Reilly Media, Inc. (2009)
Carneiro, M.G., Cupertino, T.H., Zhao, L., Rosa, J.L.: Semi-supervised semantic role labeling for Brazilian Portuguese. J. Inf. Data Manag. 8(2), 117 (2017)
Carreras, X., Màrquez, L.: Introduction to the CoNLL-2005 shared task: semantic role labeling. In: Proceedings of the CoNLL 2005, pp. 152–164. ACL (2005)
Christensen, J., Soderland, S., Etzioni, O., et al.: Semantic role labeling for open information extraction. In: Proceedings of the NAACL-HLT 2010, pp. 52–60. ACL (2010)
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12(Aug), 2493–2537 (2011)
Duran, M.S., Aluísio, S.M.: Propbank-Br: a Brazilian Treebank annotated with semantic role labels. In: LREC, pp. 1862–1867 (2012)
Fonseca, E.R., Rosa, J.L.G.: A two-step convolutional neural network approach for semantic role labeling. In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2013)
Fushiki, T.: Estimation of prediction error by using k-fold cross-validation. Stat. Comput. 21(2), 137–146 (2011)
Gal, Y., Ghahramani, Z.: A theoretically grounded application of dropout in recurrent neural networks. In: Advances in Neural Information Processing Systems, pp. 1019–1027 (2016)
Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: Proceedings of the Acoustics, Speech and Signal Processing Conference (ICASSP 2013), pp. 6645–6649. IEEE (2013)
Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5), 602–610 (2005)
Hartmann, N.S., Duran, M.S., Aluísio, S.M.: Automatic semantic role labeling on non-revised syntactic trees of journalistic texts. In: Silva, J., Ribeiro, R., Quaresma, P., Adami, A., Branco, A. (eds.) PROPOR 2016. LNCS (LNAI), vol. 9727, pp. 202–212. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-41552-9_20
He, L., Lee, K., Lewis, M., Zettlemoyer, L.: Deep semantic role labeling: what works and what’s next. In: Proceedings of the ACL 2017 (2017)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015)
Khan, A., Salim, N., Kumar, Y.J.: A framework for multi-document abstractive summarization based on semantic role labelling. Appl. Soft Comput. 30, 737–747 (2015)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kumar, A., et al.: Ask me anything: dynamic memory networks for natural language processing. In: International Conference on Machine Learning, pp. 1378–1387 (2016)
Lee, K., Lewis, M., Zettlemoyer, L.: Global neural CCG parsing with optimality guarantees. arXiv preprint arXiv:1607.01432 (2016)
Levy, O., Goldberg, Y., Dagan, I.: Improving distributional similarity with lessons learned from word embeddings. Trans. ACL 3, 211–225 (2015)
Melamud, O., McClosky, D., Patwardhan, S., Bansal, M.: The role of context types and dimensionality in learning word embeddings. In: Proceedings of NAACL-HLT 2016, pp. 1030–1040 (2016)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Pradhan, S., Ward, W., Hacioglu, K., Martin, J.H., Jurafsky, D.: Semantic role labeling using different syntactic views. In: Proceedings of the ACL 2005, ACL 2005, Stroudsburg, PA, USA, pp. 581–588. ACL (2005)
Punyakanok, V., Roth, D., Yih, W.T.: The importance of syntactic parsing and inference in semantic role labeling. Comput. Linguist. 34(2), 257–287 (2008)
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104–3112 (2014)
Täckström, O., Ganchev, K., Das, D.: Efficient inference and structured learning for semantic role labeling. Trans. ACL 3, 29–41 (2015)
Tai, K.S., Socher, R., Manning, C.D.: Improved semantic representations from tree-structured long short-term memory networks. arXiv preprint arXiv:1503.00075 (2015)
Toutanova, K., Haghighi, A., Manning, C.D.: Joint learning improves semantic role labeling. In: Proceedings of the ACL 2005, pp. 589–596. ACL (2005)
Wang, Z., Jiang, T., Chang, B., Sui, Z.: Chinese semantic role labeling with bidirectional recurrent neural networks. In: Proceedings of the EMNLP 2015, pp. 1626–1631 (2015)
Wu, D., Fung, P.: Can semantic role labeling improve SMT. In: Proceedings of the EAMT 2009, pp. 218–225 (2009)
Zhou, J., Xu, W.: End-to-end learning of semantic role labeling using recurrent neural networks. In: Proceedings of the ACL 2015, pp. 1127–1137 (2015)
Acknowledgment
This work was partially funded by ANEEL Brazil R&D Project CEMIG GT641.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Falci, D.H.M., Soares, M.A.C., Brandão, W.C., Parreiras, F.S. (2019). Using Recurrent Neural Networks for Semantic Role Labeling in Portuguese. In: Moura Oliveira, P., Novais, P., Reis, L. (eds) Progress in Artificial Intelligence. EPIA 2019. Lecture Notes in Computer Science(), vol 11805. Springer, Cham. https://doi.org/10.1007/978-3-030-30244-3_56
Download citation
DOI: https://doi.org/10.1007/978-3-030-30244-3_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30243-6
Online ISBN: 978-3-030-30244-3
eBook Packages: Computer ScienceComputer Science (R0)