Abstract
The ability for variation in language use is necessary for speakers to achieve their conversational goals, for instance when referring to objects in visual environments. We argue that diversity should not be modelled as an independent objective in dialogue, but should rather be a result or by-product of goal-oriented language generation. Different lines of work in neural language generation investigated decoding methods for generating more diverse utterances, or increasing the informativity through pragmatic reasoning. We connect those lines of work and analyze how pragmatic reasoning during decoding affects the diversity of generated image captions. We find that boosting diversity itself does not result in more pragmatically informative captions, but pragmatic reasoning does increase lexical diversity. Finally, we discuss whether the gain in informativity is achieved in linguistically plausible ways.- Anthology ID:
- 2021.sigdial-1.43
- Volume:
- Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
- Month:
- July
- Year:
- 2021
- Address:
- Singapore and Online
- Venue:
- SIGDIAL
- SIG:
- SIGDIAL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 411–422
- Language:
- URL:
- https://aclanthology.org/2021.sigdial-1.43
- DOI:
- Cite (ACL):
- Simeon Schüz, Ting Han, and Sina Zarrieß. 2021. Diversity as a By-Product: Goal-oriented Language Generation Leads to Linguistic Variation. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 411–422, Singapore and Online. Association for Computational Linguistics.
- Cite (Informal):
- Diversity as a By-Product: Goal-oriented Language Generation Leads to Linguistic Variation (Schüz et al., SIGDIAL 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.sigdial-1.43.pdf