Abstract
Multilingual pre-trained language models (PLMs) facilitate zero-shot cross-lingual transfer from rich-resource languages to low-resource languages in extractive question answering (QA) tasks. However, during fine-tuning on the QA task, the syntactic information of languages in multilingual PLMs is not always preserved or even is forgotten, which may influence the detection of answer spans for low-resource languages. In this paper, we propose an auxiliary task to predict syntactic graphs to enhance syntax information in the fine-tuning stage of the QA task to improve the answer span detection of low-resource. The syntactic graph includes Part-of-Speech (POS) information and syntax tree information without dependency parse label. We convert the syntactic graph prediction task into two subtasks to adapt the sequence input of PLMs: POS tags prediction task and syntax tree prediction task (including depth prediction of a word and distance prediction of two words). Moreover, to improve the alignment between languages, we parallel train the source language and target languages syntactic graph prediction task. Extensive experiments on three multilingual QA datasets show the effectiveness of our proposed approach.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100, 000+ questions for machine comprehension of text. In: 21st International Conference on Empirical Methods in Natural Language Processing, pp. 2383–2392. Association for Computational Linguistics. Austin, Texas, USA (2016)
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: 23rd International Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4171–4186. Association for Computational Linguistics. Minneapolis, MN, USA (2019)
Conneau, A., Lample, G.: Cross-lingual language model pretraining. In: 33rd International Conference on Neural Information Processing Systems, pp. 7057–7067. Vancouver, BC, Canada (2019)
Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. In: 58th Conference of the Association for Computational Linguistics, pp. 8440–8451. Association for Computational Linguistics. Online (2020)
Artetxe, M., Schwenk, H.: Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond. Trans. Assoc. Comput. Linguist. 7, 597–610 (2019)
Patrick, S.H., Lewis, B.O., Rinott, R., Riedel, S., Schwenk, H.: MLQA: evaluating cross-lingual extractive question answering. In: 58th Conference of the Association for Computational Linguistics, pp. 7315–7330 (2020)
Artetxe, M., Ruder, S., Yogatama, D.: On the cross-lingual transferability of monolingual representations. In: 58th Conference of the Association for Computational Linguistics, pp. 4623–4637 (2020)
Jonathan, H., et al.: TyDi QA: a Benchmark for information-seeking question answering in typologically diverse languages. Trans. Assoc. Comput. Linguist. 8, 454–470 (2020)
Yuan, F., et al.: Enhancing answer boundary detection for multilingual machine reading comprehension. In: 58th Conference of the Association for Computational Linguistics, pp. 925–934. Association for Computational Linguistics (2020)
Gangi Reddy, R., et al.: Answer span correction in machine reading comprehension. In: 25th International Conference on Empirical Methods in Natural Language Processing, pp. 2496–2501. Association for Computational Linguistics (2020)
Hewitt, J., Manning, C.D.: A structural probe for finding syntax in word representations. In: 23rd International Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4129–4138. Association for Computational Linguistics. Minneapolis, MN, USA (2019)
Chi, E.A., Hewitt, J., Manning, C.D.: Finding universal grammatical relations in multilingual BERT. In: 58th Conference of the Association for Computational Linguistics, pp. 5564–5577. Association for Computational Linguistics (2020)
Pérez-Mayos, L., Carlini, R., Ballesteros, M., Wanner, L.: On the evolution of syntactic information encoded by BERT’s contextualized representations. In: 16th Conference of the European Chapter of the Association for Computational Linguistics, pp. 2243–2258. Association for Computational Linguistics(2021)
Xu, K., Wu, L., Wang, Z., Yu, M., Chen, L., Sheinin, V.: Exploiting rich syntactic information for semantic parsing with graph-to-sequence model. In: 23th International Conference on Empirical Methods in Natural Language Processing, pp. 918–924. Association for Computational Linguistics. Brussels, Belgium (2018)
Hsu, T.-Y., Liu, C.-L., Lee, H.: Zero-shot reading comprehension by cross-lingual transfer learning with multi-lingual language representation model. In: 24th International Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp. 5932–5939. Association for Computational Linguistics. Hong Kong, China (2019)
Liu, J., Shou, L., Pei, J., Gong, M., Yang, M., Jiang, D.: Cross-lingual machine reading comprehension. In: 24th International Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp. 1586–1595. Association for Computational Linguistics. Hong Kong, China (2019)
Liu, J., Shou, L., Pei, J., Gong, M., Yang, M., Jiang, D.: Cross-lingual machine reading comprehension with language branch knowledge distillation. In: 28th International Conference on Computational Linguistics, pp. 2710–2721. International Committee on Computational Linguistics (2020)
Huang, W.-C., Huang, C., Lee, H.: Improving cross-lingual reading comprehension with self-training. arXiv preprint arXiv:2105.03627 (2021)
Gaochen Wu, Bin Xu, Yuxin Qin, Fei Kong, Bangchang Liu, Hongwen Zhao, Dejie Chang: Improving Low-resource Reading Comprehension via Cross-lingual Transposition Rethinking. arXiv preprint arXiv:2107.05002 (2021)
Jiao, J., Wang, S., Zhang, X., Wang, L., Feng, Z., Wang, J.: gMatch: knowledge base question answering via semantic matching. Knowl.-Based Syst. 228, 107270 (2021)
Hu, J., Ruder, S., Siddhant, A., Neubig, G., Firat, O., Johnson, M.: XTREME: a massively multilingual multi-task benchmark for evaluating cross-lingual generalisation. In: 37th International Conference on Machine Learning, pp. 4411–4421. Proceedings of Machine Learning Research. Virtual Event (2020)
Zeman, D., et al.: Universal dependencies 2.7 (2020). http://hdl.handle.net/11234/570 1–3424
Conneau, A., et al.: XNLI: evaluating cross-lingual sentence representations. In: 23th International Conference on Empirical Methods in Natural Language Processing, pp. 2475–2485. Association for Computational Linguistics. Brussels, Belgium (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, L., Zhu, J., Zhang, X., Zhuang, Z., Feng, Z. (2022). Enhancing Low-Resource Languages Question Answering with Syntactic Graph. In: Rage, U.K., Goyal, V., Reddy, P.K. (eds) Database Systems for Advanced Applications. DASFAA 2022 International Workshops. DASFAA 2022. Lecture Notes in Computer Science, vol 13248. Springer, Cham. https://doi.org/10.1007/978-3-031-11217-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-11217-1_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11216-4
Online ISBN: 978-3-031-11217-1
eBook Packages: Computer ScienceComputer Science (R0)