diff --git a/data/xml/2021.findings.xml b/data/xml/2021.findings.xml index d4652661ea..9890bc3539 100644 --- a/data/xml/2021.findings.xml +++ b/data/xml/2021.findings.xml @@ -7958,13 +7958,15 @@ Albert Y.S.Lam 1114–1120 This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a vast amount of unlabeled corpus, we find it highly effective and efficient to simply fine-tune BERT with a small set of labeled utterances from public datasets. Specifically, fine-tuning BERT with roughly 1,000 labeled data yields a pre-trained model – IntentBERT, which can easily surpass the performance of existing pre-trained models for few-shot intent classification on novel domains with very different semantics. The high effectiveness of IntentBERT confirms the feasibility and practicality of few-shot intent detection, and its high generalization ability across different domains suggests that intent classification tasks may share a similar underlying structure, which can be efficiently learned from a small set of labeled data. The source code can be found at https://github.com/hdzhang-code/IntentBERT. - 2021.findings-emnlp.96 + 2021.findings-emnlp.96 zhang-etal-2021-effectiveness-pre 10.18653/v1/2021.findings-emnlp.96