Cargando…
FewJoint: few-shot learning for joint dialogue understanding
Few-shot learning (FSL) is one of the key future steps in machine learning and raises a lot of attention. In this paper, we focus on the FSL problem of dialogue understanding, which contains two closely related tasks: intent detection and slot filling. Dialogue understanding has been proven to benef...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer Berlin Heidelberg
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9294856/ https://www.ncbi.nlm.nih.gov/pubmed/35874622 http://dx.doi.org/10.1007/s13042-022-01604-9 |
_version_ | 1784749935791439872 |
---|---|
author | Hou, Yutai Wang, Xinghao Chen, Cheng Li, Bohan Che, Wanxiang Chen, Zhigang |
author_facet | Hou, Yutai Wang, Xinghao Chen, Cheng Li, Bohan Che, Wanxiang Chen, Zhigang |
author_sort | Hou, Yutai |
collection | PubMed |
description | Few-shot learning (FSL) is one of the key future steps in machine learning and raises a lot of attention. In this paper, we focus on the FSL problem of dialogue understanding, which contains two closely related tasks: intent detection and slot filling. Dialogue understanding has been proven to benefit a lot from jointly learning the two sub-tasks. However, such joint learning becomes challenging in the few-shot scenarios: on the one hand, the sparsity of samples greatly magnifies the difficulty of modeling the connection between the two tasks; on the other hand, how to jointly learn multiple tasks in the few-shot setting is still less investigated. In response to this, we introduce FewJoint, the first FSL benchmark for joint dialogue understanding. FewJoint provides a new corpus with 59 different dialogue domains from real industrial API and a code platform to ease FSL experiment set-up, which are expected to advance the research of this field. Further, we find that insufficient performance of the few-shot setting often leads to noisy sharing between two sub-task and disturbs joint learning. To tackle this, we guide slot with explicit intent information and propose a novel trust gating mechanism that blocks low-confidence intent information to ensure high quality sharing. Besides, we introduce a Reptile-based meta-learning strategy to achieve better generalization in unseen few-shot domains. In the experiments, the proposed method brings significant improvements on two datasets and achieve new state-of-the-art performance. |
format | Online Article Text |
id | pubmed-9294856 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Springer Berlin Heidelberg |
record_format | MEDLINE/PubMed |
spelling | pubmed-92948562022-07-19 FewJoint: few-shot learning for joint dialogue understanding Hou, Yutai Wang, Xinghao Chen, Cheng Li, Bohan Che, Wanxiang Chen, Zhigang Int J Mach Learn Cybern Original Article Few-shot learning (FSL) is one of the key future steps in machine learning and raises a lot of attention. In this paper, we focus on the FSL problem of dialogue understanding, which contains two closely related tasks: intent detection and slot filling. Dialogue understanding has been proven to benefit a lot from jointly learning the two sub-tasks. However, such joint learning becomes challenging in the few-shot scenarios: on the one hand, the sparsity of samples greatly magnifies the difficulty of modeling the connection between the two tasks; on the other hand, how to jointly learn multiple tasks in the few-shot setting is still less investigated. In response to this, we introduce FewJoint, the first FSL benchmark for joint dialogue understanding. FewJoint provides a new corpus with 59 different dialogue domains from real industrial API and a code platform to ease FSL experiment set-up, which are expected to advance the research of this field. Further, we find that insufficient performance of the few-shot setting often leads to noisy sharing between two sub-task and disturbs joint learning. To tackle this, we guide slot with explicit intent information and propose a novel trust gating mechanism that blocks low-confidence intent information to ensure high quality sharing. Besides, we introduce a Reptile-based meta-learning strategy to achieve better generalization in unseen few-shot domains. In the experiments, the proposed method brings significant improvements on two datasets and achieve new state-of-the-art performance. Springer Berlin Heidelberg 2022-07-18 2022 /pmc/articles/PMC9294856/ /pubmed/35874622 http://dx.doi.org/10.1007/s13042-022-01604-9 Text en © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic. |
spellingShingle | Original Article Hou, Yutai Wang, Xinghao Chen, Cheng Li, Bohan Che, Wanxiang Chen, Zhigang FewJoint: few-shot learning for joint dialogue understanding |
title | FewJoint: few-shot learning for joint dialogue understanding |
title_full | FewJoint: few-shot learning for joint dialogue understanding |
title_fullStr | FewJoint: few-shot learning for joint dialogue understanding |
title_full_unstemmed | FewJoint: few-shot learning for joint dialogue understanding |
title_short | FewJoint: few-shot learning for joint dialogue understanding |
title_sort | fewjoint: few-shot learning for joint dialogue understanding |
topic | Original Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9294856/ https://www.ncbi.nlm.nih.gov/pubmed/35874622 http://dx.doi.org/10.1007/s13042-022-01604-9 |
work_keys_str_mv | AT houyutai fewjointfewshotlearningforjointdialogueunderstanding AT wangxinghao fewjointfewshotlearningforjointdialogueunderstanding AT chencheng fewjointfewshotlearningforjointdialogueunderstanding AT libohan fewjointfewshotlearningforjointdialogueunderstanding AT chewanxiang fewjointfewshotlearningforjointdialogueunderstanding AT chenzhigang fewjointfewshotlearningforjointdialogueunderstanding |