Abstract
This paper tackles the reduction of redundant repeating generation that is often observed in RNN-based encoder-decoder models. Our basic idea is to jointly estimate the upper-bound frequency of each target vocabulary in the encoder and control the output words based on the estimation in the decoder. Our method shows significant improvement over a strong RNN-based encoder-decoder baseline and achieved its best results on an abstractive summarization benchmark.
| Original language | English |
|---|---|
| Title of host publication | Short Papers |
| Publisher | Association for Computational Linguistics (ACL) |
| Pages | 291-297 |
| Number of pages | 7 |
| ISBN (Electronic) | 9781510838604 |
| DOIs | |
| Publication status | Published - 2017 Jan 1 |
| Externally published | Yes |
| Event | 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spain Duration: 2017 Apr 3 → 2017 Apr 7 |
Publication series
| Name | 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference |
|---|---|
| Volume | 2 |
Other
| Other | 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 |
|---|---|
| Country | Spain |
| City | Valencia |
| Period | 17/4/3 → 17/4/7 |
ASJC Scopus subject areas
- Linguistics and Language
- Language and Linguistics
Fingerprint Dive into the research topics of 'Cutting-off redundant repeating generations for neural abstractive summarization'. Together they form a unique fingerprint.
Cite this
Suzuki, J., & Nagata, M. (2017). Cutting-off redundant repeating generations for neural abstractive summarization. In Short Papers (pp. 291-297). (15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference; Vol. 2). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/e17-2047