Abstract
In this paper, we propose using deep neural networks to extract important information from Vietnamese legal questions, a fundamental task towards building a question answering system in the legal domain. Given a legal question in natural language, the goal is to extract all the segments that contain the needed information to answer the question. We introduce a deep model that solves the task in three stages. First, our model leverages recent advanced autoencoding language models to produce contextual word embeddings, which are then combined with character-level and POS-tag information to form word representations. Next, bidirectional long short-term memory networks are employed to capture the relations among words and generate sentence-level representations. At the third stage, borrowing ideas from graph-based dependency parsing methods which provide a global view on the input sentence, we use biaffine classifiers to estimate the probability of each pair of start-end words to be an important segment. Experimental results on a public Vietnamese legal dataset show that our model outperforms the previous work by a large margin, achieving 94.79% in the F\(_1\) score. The results also prove the effectiveness of using contextual features extracted from pre-trained language models combined with other types of features such as character-level and POS-tag features when training on a limited dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bach, N.X., Cham, L.T.N., Thien, T.H.N., Phuong, T.M.: Question analysis for vietnamese legal question answering. In: Proceedings of KSE, pp. 154–159 (2017)
Xuan Bach, N., Khuong Duy, T., Minh Phuong, T.: A POS tagging model for Vietnamese social media text using BiLSTM-CRF with rich features. In: Nayak, A.C., Sharma, A. (eds.) PRICAI 2019. LNCS (LNAI), vol. 11672, pp. 206–219. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29894-4_16
Bach, N.X., Thanh, P.D., Oanh, T.T.: Question analysis towards a Vietnamese question answering system in the education domain. Cybern. Inf. Technol. 20(1), 112–128 (2020)
Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. TACL 5, 135–146 (2017)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171–4186 (2019)
Dozat, T., Manning, C.D.: Deep biaffine attention for neural dependency parsing. In: Proceedings of ICLR (2017)
Duong, H.-T., Ho, B.-Q.: A Vietnamese question answering system in Vietnam’s legal documents. In: Saeed, K., Snášel, V. (eds.) CISIM 2014. LNCS, vol. 8838, pp. 186–197. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-45237-0_19
Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5–6), 602–610 (2005)
He, Z., Wang, X., Wei, W., Feng, S., Mao, X., Jiang, S.: A survey on recent advances in sequence labeling from deep learning models. arXiv preprint arXiv:2011.06727v1 (2020)
He, P., Liu, X., Gao, J., Chen, W.: DeBERTa: decoding-enhanced BERT with disentangled attention. In: Proceedings of ICLR (2021)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Kien, P.M., Nguyen, H.T., Bach, N.X., Tran, V., Nguyen, M.L., Phuong, T.M.: Answering legal questions by learning neural attentive text representation. In: Proceedings of COLING, pp. 988–998 (2020)
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of EMNLP, pp. 1746–1751 (2014)
Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of ICML, pp. 282–289 (2001)
Le-Hong, P., Bui, D.T.: A factoid question answering system for Vietnamese. In: Proceedings of Web Conference Companion, Workshop Track, pp. 1049–1055 (2018)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(110), 2278–2324 (1998)
Li, Y., Li, Z., Zhang, M., Wang, R., Li, S., Si, L.: Self-attentive biaffine dependency parsing. In: Proceedings of IJCAI, pp. 5067–5073 (2019)
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692v1 (2019)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: Proceedings of ICLR (2019)
Mikolov, T., Chen, K., Corrado, G.S., Dean, J.: Efficient estimation of word representations in vector space. In: Proceedings of ICLR (2013)
Mrini, K., Dernoncourt, F., Tran, Q.H., Bui, T., Chang, W., Nakashole, N.: Rethinking self-attention: towards interpretability in neural parsing. In: Proceedings of EMNLP Findings, pp. 731–742 (2020)
Nguyen, D.Q., Nguyen, D.Q., Pham., S.Q.: A Vietnamese question answering system. In: Proceedings of KSE, pp. 26–32 (2009)
Nguyen, D.Q., Verspoor, K.: End-to-end neural relation extraction using deep biaffine attention. In: Azzopardi, L., Stein, B., Fuhr, N., Mayr, P., Hauff, C., Hiemstra, D. (eds.) ECIR 2019. LNCS, vol. 11437, pp. 729–738. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-15712-8_47
Nguyen, D.Q., Nguyen, A.T.: PhoBERT: pre-trained language models for Vietnamese. In: Proceedings of EMNLP, pp. 1037–1042 (2020)
Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Proceedings of EMNLP, pp. 1532–1543 (2014)
Song, X., Petrak, J., Roberts, A.: A deep neural network sentence level classification method with context information. In: Proceedings of EMNLP, pp. 900–904 (2018)
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of NIPS (2014)
Tran, V.M., Nguyen, V.D., Tran, O.T., Pham, U.T.T., Ha, T.Q.: An experimental study of Vietnamese question answering system. In: Proceedings of IALP, pp. 152–155 (2009)
Tran, V.M., Le, D.T., Tran, X.T., Nguyen, T.T.: A model of Vietnamese person named entity question answering system. In: Proceedings of PACLIC, pp. 325–332 (2012)
Tran, O.T., Ngo, B.X., Le Nguyen, M., Shimazu, A.: Answering legal questions by mining reference information. In: Nakano, Y., Satoh, K., Bekki, D. (eds.) JSAI-isAI 2013. LNCS (LNAI), vol. 8417, pp. 214–229. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10061-6_15
Vaswani, A., et al.: Attention is all you need. In: Proceedings of NIPS, pp. 6000–6010 (2017)
Vu, T., Nguyen, D.Q., Nguyen, D.Q., Dras, M., Johnson, M.: VnCoreNLP: a Vietnamese natural language processing toolkit. In: Proceedings NAACL Demonstrations, pp. 56–60 (2018)
Yadav, V., Bethard, S.: A survey on recent advances in named entity recognition from deep learning models. In: Proceedings of COLING, pp. 2145–2158 (2018)
Yang, K., Deng, J.: Strongly incremental constituency parsing with graph neural networks. In: Proceedings of NeurIPS (2020)
Yang, S., Wang, Y., Chu, X.: A survey of deep learning techniques for neural machine translation. arXiv preprint arXiv:2002.07526v1 (2020)
Yu, J., Bohnet, B., Poesio, M.: Named entity recognition as dependency parsing. In: Proceedings of ACL, pp. 6470–6476 (2020)
Acknowledgements
We would like to thank FPT Technology Research Institute, FPT University for financial support which made this work possible.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Anh Tu, N., Thi Thu Uyen, H., Minh Phuong, T., Xuan Bach, N. (2021). Analyzing Vietnamese Legal Questions Using Deep Neural Networks with Biaffine Classifiers. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13109. Springer, Cham. https://doi.org/10.1007/978-3-030-92270-2_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-92270-2_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92269-6
Online ISBN: 978-3-030-92270-2
eBook Packages: Computer ScienceComputer Science (R0)