QAID: Question Answering Inspired Few-Shot Intent Detection

Abstract

Intent detection with semantically similar fine-grained intents is a challenging task. To address it, we reformulate intent detection as a question-answering retrieval task by treating utterances and intent names as questions and answers. To that end, we utilize a question-answering retrieval architecture and adopt a two stages training schema with batch contrastive loss. In the pre-training stage, we improve query representations through self-supervised training. Then, in the fine-tuning stage, we increase contextualized token-level similarity scores between queries and answers from the same intent. Our results on three few-shot intent detection benchmarks achieve state-of-the-art performance.

Cite

Text

Yehudai et al. "QAID: Question Answering Inspired Few-Shot Intent Detection." International Conference on Learning Representations, 2023.

Markdown

[Yehudai et al. "QAID: Question Answering Inspired Few-Shot Intent Detection." International Conference on Learning Representations, 2023.](https://mlanthology.org/iclr/2023/yehudai2023iclr-qaid/)

BibTeX

@inproceedings{yehudai2023iclr-qaid,
  title     = {{QAID: Question Answering Inspired Few-Shot Intent Detection}},
  author    = {Yehudai, Asaf and Vetzler, Matan and Mass, Yosi and Lazar, Koren and Cohen, Doron and Carmeli, Boaz},
  booktitle = {International Conference on Learning Representations},
  year      = {2023},
  url       = {https://mlanthology.org/iclr/2023/yehudai2023iclr-qaid/}
}