Abstract
We improve the informativeness of models for conditional text generation using techniques from computational pragmatics. These techniques formulate language production as a game between speakers and listeners, in which a speaker should generate output text that a listener can use to correctly identify the original input that the text describes. While such approaches are widely used in cognitive science and grounded language learning, they have received less attention for more standard language generation tasks. We consider two pragmatic modeling methods for text generation: one where pragmatics is imposed by information preservation, and another where pragmatics is imposed by explicit modeling of distractors. We find that these methods improve the performance of strong existing systems for abstractive summarization and generation from structured meaning representations.- Anthology ID:
- N19-1410
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4060–4067
- Language:
- URL:
- https://aclanthology.org/N19-1410
- DOI:
- 10.18653/v1/N19-1410
- Cite (ACL):
- Sheng Shen, Daniel Fried, Jacob Andreas, and Dan Klein. 2019. Pragmatically Informative Text Generation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4060–4067, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Pragmatically Informative Text Generation (Shen et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/N19-1410.pdf
- Code
- additional community code
- Data
- CNN/Daily Mail, E2E