https://scholars.lib.ntu.edu.tw/handle/123456789/413073
標題: | Precise Description Generation for Knowledge Base Entities with Local Pointer Network | 作者: | Yeh S.-H. Huang H.-H. HSIN-HSI CHEN |
關鍵字: | Knowledge base;Natural language generation;Pointer network | 公開日期: | 2019 | 起(迄)頁: | 214-221 | 來源出版物: | 2018 IEEE/WIC/ACM International Conference on Web Intelligence | 摘要: | Verbalization of knowledge base (KB) facts about an entity allows users to absorb information from KB more easily. The drawback of most previous work is that they cannot generalize to unseen frames. This work introduces the task of precise KB verbalization that is aimed at generating an exact description for the given factual triples. We propose a novel sequence-to-sequence (seq2seq) model with the local pointer network to deal with this task. The approach to training data construction is also explored. Experimental results show our method improves the performances in terms of Meteor and slot error rates. Human evaluation is also performed to confirm the effectiveness of our model. ? 2018 IEEE. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/413073 | ISBN: | 9781538673256 | DOI: | 10.1109/WI.2018.00-87 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。