Publications-Proceedings
Article View/Open
Publication Export
-
題名 Numeracy-600K: Learning Numeracy for Detecting Exaggerated Information in Market Comments 作者 黃瀚萱
Huang, Hen-Hsen
Chen, Chung-Chi
Takamura, Hiroya
Chen, Hsin-Hsi貢獻者 資科系 日期 2019-07 上傳時間 4-Jun-2021 14:43:21 (UTC+8) 摘要 In this paper, we attempt to answer the question of whether neural network models can learn numeracy, which is the ability to predict the magnitude of a numeral at some specific position in a text description. A large benchmark dataset, called Numeracy-600K, is provided for the novel task. We explore several neural network models including CNN, GRU, BiGRU, CRNN, CNN-capsule, GRU-capsule, and BiGRU-capsule in the experiments. The results show that the BiGRU model gets the best micro-averaged F1 score of 80.16%, and the GRU-capsule model gets the best macroaveraged F1 score of 64.71%. Besides discussing the challenges through comprehensive experiments, we also present an important application scenario, i.e., detecting exaggerated information, for the task. 關聯 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, ACL, pp.6307–6313 資料類型 conference DOI http://dx.doi.org/10.18653/v1/P19-1635 dc.contributor 資科系 dc.creator (作者) 黃瀚萱 dc.creator (作者) Huang, Hen-Hsen dc.creator (作者) Chen, Chung-Chi dc.creator (作者) Takamura, Hiroya dc.creator (作者) Chen, Hsin-Hsi dc.date (日期) 2019-07 dc.date.accessioned 4-Jun-2021 14:43:21 (UTC+8) - dc.date.available 4-Jun-2021 14:43:21 (UTC+8) - dc.date.issued (上傳時間) 4-Jun-2021 14:43:21 (UTC+8) - dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/135528 - dc.description.abstract (摘要) In this paper, we attempt to answer the question of whether neural network models can learn numeracy, which is the ability to predict the magnitude of a numeral at some specific position in a text description. A large benchmark dataset, called Numeracy-600K, is provided for the novel task. We explore several neural network models including CNN, GRU, BiGRU, CRNN, CNN-capsule, GRU-capsule, and BiGRU-capsule in the experiments. The results show that the BiGRU model gets the best micro-averaged F1 score of 80.16%, and the GRU-capsule model gets the best macroaveraged F1 score of 64.71%. Besides discussing the challenges through comprehensive experiments, we also present an important application scenario, i.e., detecting exaggerated information, for the task. dc.format.extent 470075 bytes - dc.format.mimetype application/pdf - dc.relation (關聯) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, ACL, pp.6307–6313 dc.title (題名) Numeracy-600K: Learning Numeracy for Detecting Exaggerated Information in Market Comments dc.type (資料類型) conference dc.identifier.doi (DOI) 10.18653/v1/P19-1635 dc.doi.uri (DOI) http://dx.doi.org/10.18653/v1/P19-1635
