Abstract：This paper proposed a reading comprehension model based on Bi-Directional Attention Flow (BiDAF) network. It predicts the answers using complete paragraphs and the results outperformed baseline system. The fastText is applied to train word embedding to include contextual information. The ensemble learning is adopted to improve performance and stability. Specifically, for the Yes/No questions, this paper ensembles two classification models based on attention and similarity mechanism, respectively. The model reaches a ROUGE-L score of 56.57 and a BLEU-4 score of 48.03 in the MRC 2018.
[1] Pranav Rajpurkar,et al.SQu AD:100,000+ questions for machine comprehension of text[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing,2016. [2] Tri Nguyen,et al.MS MARCO:A human generated machine reading comprehension dataset.CoRR,abs/1611.09268,2016. [3] C Shao,et al.2018 DRCD:a Chinese Machine Reading Comprehension Dataset[J].arXiv pre-print arXiv:1806.00920,2018. [4] Wei He,DuReader:a Chinese Machine Reading Comprehension Dataset from Real-world Applications [J].arXiv preprint arXiv:1711.05073,2018. [5] M Seo,A et al.Bidirectional attention flow for machine comprehension[J].arXiv pre-print arXiv:1611.01603,2016. [6] Piotr Bojanowski,et al.Enriching word vectors with subword information[C]//Proceedings of TACL 5:2017:135-146. [7] Tomas Mikolov,et al.Distributed representations of words and phrases and their compositionality[C]//Proceedings of the NIPS,2013. [8] S Hochreiter,J Schmidhuber.Long short-term memory[J].Neural Computation,1997:9(8):1735-1780. [9] 孙茂松,等.THULAC:一个高效的中文词法分析工具包[EB/OL].2016.http://thulac.tinunlp.org/. [10] Basant Agarwal,et al.A Deep Network Model for Paraphrase Detection in Short Text Messages[J].arXiv pre-print arXiv:1712.02820,2017. [11] Chin-Yew Lin.Rouge:A package for automatic evaluation of summaries[C]//Proceedings of Text Summarization Branches Out:Proceedings of the ACL-04 Workshop,2014:74-81. [12] Kishore Papineni,et al.Bleu:a method for automatic evaluation of machine translation[C]//Proceedings of 40th Annual Meeting of the Association for Computational Linguistics,2002:311-318.
2018, Vol. 32 
