Example-Driven Intent Prediction with Observers

Shikib Mehri, Mihail Eric


Abstract
A key challenge of dialog systems research is to effectively and efficiently adapt to new domains. A scalable paradigm for adaptation necessitates the development of generalizable models that perform well in few-shot settings. In this paper, we focus on the intent classification problem which aims to identify user intents given utterances addressed to the dialog system. We propose two approaches for improving the generalizability of utterance classification models: (1) observers and (2) example-driven training. Prior work has shown that BERT-like models tend to attribute a significant amount of attention to the [CLS] token, which we hypothesize results in diluted representations. Observers are tokens that are not attended to, and are an alternative to the [CLS] token as a semantic representation of utterances. Example-driven training learns to classify utterances by comparing to examples, thereby using the underlying encoder as a sentence similarity model. These methods are complementary; improving the representation through observers allows the example-driven model to better measure sentence similarities. When combined, the proposed methods attain state-of-the-art results on three intent prediction datasets (banking77, clinc150, hwu64) in both the full data and few-shot (10 examples per intent) settings. Furthermore, we demonstrate that the proposed approach can transfer to new intents and across datasets without any additional training.
Anthology ID:
2021.naacl-main.237
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2979–2992
Language:
URL:
https://aclanthology.org/2021.naacl-main.237
DOI:
10.18653/v1/2021.naacl-main.237
Bibkey:
Cite (ACL):
Shikib Mehri and Mihail Eric. 2021. Example-Driven Intent Prediction with Observers. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2979–2992, Online. Association for Computational Linguistics.
Cite (Informal):
Example-Driven Intent Prediction with Observers (Mehri & Eric, NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.237.pdf
Code
 alexa/dialoglue
Data
CLINC150