Linguistically-Informed Specificity and Semantic Plausibility for Dialogue Generation

Wei-Jen Ko, Greg Durrett, Junyi Jessy Li


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
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
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/N19-1349.pdf
Video:
 https://vimeo.com/364782035
Data
CoLAPERSONA-CHAT