A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss
| Autor: | Ming-Ying Lee, Jing Tang, Kerui Min, Chieh-Kai Lin, Min Sun, Wan-Ting Hsu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Computer science business.industry media_common.quotation_subject 02 engineering and technology Unified Model 010501 environmental sciences computer.software_genre 01 natural sciences Automatic summarization Simple (abstract algebra) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Paragraph Function (engineering) business Computation and Language (cs.CL) computer Natural language processing 0105 earth and related environmental sciences media_common |
| Zdroj: | ACL (1) |
| DOI: | 10.18653/v1/p18-1013 |
| Popis: | 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. 9 pages, ACL 2018 oral. Project page: https://hsuwanting.github.io/unified_summ/. Code: https://github.com/HsuWanTing/unified-summarization |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|