Imagination is All You Need! Curved Contrastive Learning for Abstract Sequence Modeling Utilized on Long Short-Term Dialogue Planning

Justus-Jonas Erker, Stefan Schaffer, Gerasimos Spanakis


Abstract
Inspired by the curvature of space-time, we introduce Curved Contrastive Learning (CCL), a novel representation learning technique for learning the relative turn distance between utterance pairs in multi-turn dialogues. The resulting bi-encoder models can guide transformers as a response ranking model towards a goal in a zero-shot fashion by projecting the goal utterance and the corresponding reply candidates into a latent space. Here the cosine similarity indicates the distance/reachability of a candidate utterance toward the corresponding goal. Furthermore, we explore how these forward-entailing language representations can be utilized for assessing the likelihood of sequences by the entailment strength i.e. through the cosine similarity of its individual members (encoded separately) as an emergent property in the curved space. These non-local properties allow us to imagine the likelihood of future patterns in dialogues, specifically by ordering/identifying future goal utterances that are multiple turns away, given a dialogue context. As part of our analysis, we investigate characteristics that make conversations (un)plannable and find strong evidence of planning capability over multiple turns (in 61.56% over 3 turns) in conversations from the DailyDialog dataset. Finally, we show how we achieve higher efficiency in sequence modeling tasks compared to previous work thanks to our relativistic approach, where only the last utterance needs to be encoded and computed during inference.
Anthology ID:
2023.findings-acl.319
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5152–5173
Language:
URL:
https://aclanthology.org/2023.findings-acl.319
DOI:
10.18653/v1/2023.findings-acl.319
Bibkey:
Cite (ACL):
Justus-Jonas Erker, Stefan Schaffer, and Gerasimos Spanakis. 2023. Imagination is All You Need! Curved Contrastive Learning for Abstract Sequence Modeling Utilized on Long Short-Term Dialogue Planning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5152–5173, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Imagination is All You Need! Curved Contrastive Learning for Abstract Sequence Modeling Utilized on Long Short-Term Dialogue Planning (Erker et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.319.pdf