Generating Repetitions with Appropriate Repeated Words

Toshiki Kawamoto, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura


Abstract
A repetition is a response that repeats words in the previous speaker’s utterance in a dialogue. Repetitions are essential in communication to build trust with others, as investigated in linguistic studies. In this work, we focus on repetition generation. To the best of our knowledge, this is the first neural approach to address repetition generation. We propose Weighted Label Smoothing, a smoothing method for explicitly learning which words to repeat during fine-tuning, and a repetition scoring method that can output more appropriate repetitions during decoding. We conducted automatic and human evaluations involving applying these methods to the pre-trained language model T5 for generating repetitions. The experimental results indicate that our methods outperformed baselines in both evaluations.
Anthology ID:
2022.naacl-main.62
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
852–859
Language:
URL:
https://aclanthology.org/2022.naacl-main.62
DOI:
10.18653/v1/2022.naacl-main.62
Bibkey:
Cite (ACL):
Toshiki Kawamoto, Hidetaka Kamigaito, Kotaro Funakoshi, and Manabu Okumura. 2022. Generating Repetitions with Appropriate Repeated Words. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 852–859, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Generating Repetitions with Appropriate Repeated Words (Kawamoto et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.62.pdf
Code
 titech-nlp/repetition-generation