Abstract
Sequence-to-sequence models for open-domain dialogue generation tend to favor generic, uninformative responses. Past work has focused on word frequency-based approaches to improving specificity, such as penalizing responses with only common words. In this work, we examine whether specificity is solely a frequency-related notion and find that more linguistically-driven specificity measures are better suited to improving response informativeness. However, we find that forcing a sequence-to-sequence model to be more specific can expose a host of other problems in the responses, including flawed discourse and implausible semantics. We rerank our model’s outputs using externally-trained classifiers targeting each of these identified factors. Experiments show that our final model using linguistically motivated specificity and plausibility reranking improves the informativeness, reasonableness, and grammatically of responses.- Anthology ID:
- N19-1349
- 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
- Editors:
- Jill Burstein, Christy Doran, Thamar Solorio
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3456–3466
- Language:
- URL:
- https://aclanthology.org/N19-1349
- DOI:
- 10.18653/v1/N19-1349
- Cite (ACL):
- Wei-Jen Ko, Greg Durrett, and Junyi Jessy Li. 2019. Linguistically-Informed Specificity and Semantic Plausibility for Dialogue 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 3456–3466, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Linguistically-Informed Specificity and Semantic Plausibility for Dialogue Generation (Ko et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/naacl24-info/N19-1349.pdf
- Code
- wjko2/Linguistically-Informed-Specificity-and-Semantic-Plausibility-for-Dialogue-Generation
- Data
- CoLA