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.
Original language | English |
---|---|
Title of host publication | Findings of the Association for Computational Linguistics, ACL 2023 |
Place of Publication | Toronto, Canada |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 5152-5173 |
Number of pages | 22 |
ISBN (Electronic) | 9781959429623 |
DOIs | |
Publication status | Published - 1 Jul 2023 |
Event | 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Canada, Toronto, Canada Duration: 9 Jul 2023 → 14 Jul 2023 https://2023.aclweb.org/ |
Publication series
Series | Association for Computational Linguistics. Annual Meeting. Conference Proceedings |
---|---|
ISSN | 0736-587X |
Conference
Conference | 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 |
---|---|
Abbreviated title | ACL 2023 |
Country/Territory | Canada |
City | Toronto |
Period | 9/07/23 → 14/07/23 |
Internet address |