Abstract | ||
---|---|---|
Neural models are being widely applied for text summarization, including headline generation, and are typically trained using a set of document-headline pairs. In a large document set, documents can usually be grouped into various topics, and documents within a certain topic may exhibit specific summarization patterns. Most existing neural models, however, have not taken the topic information of documents into consideration. This paper categorizes documents into multiple topics, since documents within the same topic have similar content and share similar summarization patterns. By taking advantage of document topic information, this study proposes a topic-sensitive neural headline generation model (TopicNHG). It is evaluated on a real-world dataset, large scale Chinese short text summarization dataset. Experimental results show that it outperforms several baseline systems on each topic and achieves comparable performance with the state-of-the-art system. This indicates that TopicNHG can generate more accurate headlines guided by document topics. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/s11432-019-2657-8 | SCIENCE CHINA-INFORMATION SCIENCES |
Keywords | DocType | Volume |
neural networks,sequence to sequence learning,topic,LDA,headline generation | Journal | 63 |
Issue | ISSN | Citations |
8 | 1674-733X | 0 |
PageRank | References | Authors |
0.34 | 31 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ayana | 1 | 0 | 0.34 |
ZiYun Wang | 2 | 12 | 1.16 |
Lei Xu | 3 | 0 | 0.34 |
Zhiyuan Liu | 4 | 2037 | 123.68 |
Maosong Sun | 5 | 2293 | 162.86 |