Title | ||
---|---|---|
A Unified Model For Extractive And Abstractive Summarization Using Inconsistency Loss |
Abstract | ||
---|---|---|
We propose a unified model combining the strength of extractive and abstractive summarization. On the one hand, a simple extractive model can obtain sentence-level attention with high ROUGE scores but less readable. On the other hand, a more complicated abstractive model can obtain word-level dynamic attention to generate a more readable paragraph. In our model, sentence-level attention is used to modulate the word-level attention such that words in less attended sentences are less likely to be generated. Moreover, a novel inconsistency loss function is introduced to penalize the inconsistency between two levels of attentions. By end-to-end training our model with the inconsistency loss and original losses of extractive and abstractive models, we achieve state-of-the-art ROUGE scores while being the most informative and readable summarization on the CNN/Daily Mail dataset in a solid human evaluation. |
Year | DOI | Venue |
---|---|---|
2018 | 10.18653/v1/p18-1013 | PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1 |
Field | DocType | Volume |
Automatic summarization,Computer science,Paragraph,Natural language processing,Artificial intelligence,Unified Model | Journal | abs/1805.06266 |
Citations | PageRank | References |
9 | 0.45 | 15 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wan Ting Hsu | 1 | 28 | 1.11 |
Chieh-Kai Lin | 2 | 9 | 0.45 |
Ming-Ying Lee | 3 | 9 | 0.45 |
Kerui Min | 4 | 9 | 0.79 |
Tang, J. | 5 | 42 | 3.93 |
Min Sun | 6 | 1083 | 59.15 |