Abstract
We propose a method to control the specificity of responses while maintaining the consistency with the utterances. We first design a metric based on pointwise mutual information, which measures the co-occurrence degree between an utterance and a response. To control the specificity of generated responses, we add the distant supervision based on the co-occurrence degree and a PMI-based word prediction mechanism to a sequence-to-sequence model. With these mechanisms, our model outputs the words with optimal specificity for a given specificity control variable. In experiments with open-domain dialogue corpora, automatic and human evaluation results confirm that our model controls the specificity of the response more sensitively than the conventional model and can generate highly consistent responses.- Anthology ID:
- 2020.findings-emnlp.396
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4418–4427
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.396
- DOI:
- 10.18653/v1/2020.findings-emnlp.396
- Cite (ACL):
- Junya Takayama and Yuki Arase. 2020. Consistent Response Generation with Controlled Specificity. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4418–4427, Online. Association for Computational Linguistics.
- Cite (Informal):
- Consistent Response Generation with Controlled Specificity (Takayama & Arase, Findings 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.findings-emnlp.396.pdf
- Data
- DailyDialog