Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders

Yuwei Zhang, Siffi Singh, Sailik Sengupta, Igor Shalyminov, Hang Su, Hwanjun Song, Saab Mansour


Abstract
Conversational systems often rely on embedding models for intent classification and intent clustering tasks. The advent of Large Language Models (LLMs), which enable instructional embeddings allowing one to adjust semantics over the embedding space using prompts, are being viewed as a panacea for these downstream conversational tasks. However, traditional evaluation benchmarks rely solely on task metrics that don’t particularly measure gaps related to semantic understanding. Thus, we propose an intent semantic toolkit that gives a more holistic view of intent embedding models by considering three tasks– (1) intent classification, (2) intent clustering, and (3) a novel triplet task. The triplet task gauges the model’s understanding of two semantic concepts paramount in real-world conversational systems– negation and implicature. We observe that current embedding models fare poorly in semantic understanding of these concepts. To address this, we propose a pre-training approach to improve the embedding model by leveraging augmentation with data generated by an auto-regressive model and a contrastive loss term. Our approach improves the semantic understanding of the intent embedding model on the aforementioned linguistic dimensions while slightly effecting their performance on downstream task metrics.
Anthology ID:
2024.acl-long.33
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
552–567
Language:
URL:
https://aclanthology.org/2024.acl-long.33
DOI:
10.18653/v1/2024.acl-long.33
Bibkey:
Cite (ACL):
Yuwei Zhang, Siffi Singh, Sailik Sengupta, Igor Shalyminov, Hang Su, Hwanjun Song, and Saab Mansour. 2024. Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 552–567, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders (Zhang et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.33.pdf