Abstract
Span extraction is an important task of machine reading comprehension (MRC). Traditionally, for a question, the answer is expected to be a single text span from the given context. However, in practice, the answer to a question may exist in multiple spans. Besides, multiple answers to a question may be of different granularity and hierarchically related to each other. In this paper, we propose a simple but effective pipeline to solve the hierarchical multi-answer questions with conditions, an evaluation task introduced in CCSK 2022. The pipeline mainly contains two components: the answer span detection and relation classification. Answer span detection focuses on finding multiple answer spans while relation classification aims to determine whether there is a relationship between two answers. In addition, some helpful strategies are also introduced. Finally, our pipeline achieved an F1 score of 0.759 on online testing data and ranking second among 181 teams.
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
Elad, S., Avia, E., Mor, S., Amir, G., Jonathan, B.: A simple and effective model for answering multi-span questions. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3074–3080 (2020)
Tan, C., Qiu, W., Chen, M., Wang, R., Huang, F.: Boundary enhanced neural span classification for nested named entity recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 05, pp. 9016-9023 (2020)
Li, X., Feng, J., Meng, Y., Han, Q., Wu, F., Li, J.: A Unified MRC Framework for Named Entity Recognition, pp. 5849–5859 (2020)
Cui, Y., Yang, Z., Liu, T.: PERT: Pre-training BERT with Permuted Language Model (2022)
Xiao, D., et al.: ERNIE-Gram: pre-training with explicitly N-gram masked language modeling for natural language understanding, 1702–1715 (2021)
Cui, Y., Che, W., Liu, T., Qin, B., Wang, S., Hu, G.: Revisiting pre-trained models for chinese natural language processing. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 657–668 (2020).
Zhong, Z., Chen, D.: A frustratingly easy approach for entity and relation extraction. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 50–61 (2021)
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38–45 (2020)
Lu, Y., et al.: Unified Structure Generation for Universal Information Extraction. ACL (2022)
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 Singapore Pte Ltd.
About this paper
Cite this paper
Teng, B., Wang, X., lv, X., Zhang, X., An, B. (2022). A Coarse Pipeline to Solve Hierarchical Multi-answer Questions with Conditions. In: Zhang, N., Wang, M., Wu, T., Hu, W., Deng, S. (eds) CCKS 2022 - Evaluation Track. CCKS 2022. Communications in Computer and Information Science, vol 1711. Springer, Singapore. https://doi.org/10.1007/978-981-19-8300-9_2
Download citation
DOI: https://doi.org/10.1007/978-981-19-8300-9_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8299-6
Online ISBN: 978-981-19-8300-9
eBook Packages: Computer ScienceComputer Science (R0)