應用階層可解構式注意力模型於新聞立場辨識任務

Chen Yu Hunag, Chia Hui Chang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

摘要

The goal of News Stance Detection task is to detect whether the stance of a news article is neutral, approval or opposition with respect to a given query. The task is similar to Natural Language Inference (NLI) task, which aims to determine if one given statement (a premise) semantically entails another given statement (a hypothesis). Since most news articles hold neutral stances with respect to the given query, the training data is often unbalanced. In this paper, we proposed a Hierarchical Model based on the Decomposable Attention Model for NLI tasks to compare individual sentences with the given query and jointly predict the stance of the complete article. For the data imbalance problem, we heuristically create opposite queries and label supporting news articles from unrelated ones of the original query to identify unrelated news articles. The experiment result showed that the performance of our architecture is better than other models.

貢獻的翻譯標題A Hierarchical Decomposable Attention Model for News Stance
原文繁體中文
主出版物標題ROCLING 2020 - 32nd Conference on Computational Linguistics and Speech Processing
編輯Jenq-Haur Wang, Ying-Hui Lai, Lung-Hao Lee, Kuan-Yu Chen, Hung-Yi Lee, Chi-Chun Lee, Syu-Siang Wang, Hen-Hsen Huang, Chuan-Ming Liu
發行者The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
頁面35-49
頁數15
ISBN(電子)9789869576932
出版狀態已出版 - 2020
事件32nd Conference on Computational Linguistics and Speech Processing, ROCLING 2020 - Taipei, Taiwan
持續時間: 24 9月 202026 9月 2020

出版系列

名字ROCLING 2020 - 32nd Conference on Computational Linguistics and Speech Processing

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???32nd Conference on Computational Linguistics and Speech Processing, ROCLING 2020
國家/地區Taiwan
城市Taipei
期間24/09/2026/09/20

Keywords

  • Attention Mechanism
  • Discourse Analysis
  • Natural Language Inference
  • News Stance Detection

指紋

深入研究「應用階層可解構式注意力模型於新聞立場辨識任務」主題。共同形成了獨特的指紋。

引用此