@inproceedings{krone-etal-2020-learning,
title = "Learning to Classify Intents and Slot Labels Given a Handful of Examples",
author = "Krone, Jason and
Zhang, Yi and
Diab, Mona",
editor = "Wen, Tsung-Hsien and
Celikyilmaz, Asli and
Yu, Zhou and
Papangelis, Alexandros and
Eric, Mihail and
Kumar, Anuj and
Casanueva, I{\~n}igo and
Shah, Rushin",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlp4convai-1.12",
doi = "10.18653/v1/2020.nlp4convai-1.12",
pages = "96--108",
abstract = "Intent classification (IC) and slot filling (SF) are core components in most goal-oriented dialogue systems. Current IC/SF models perform poorly when the number of training examples per class is small. We propose a new few-shot learning task, few-shot IC/SF, to study and improve the performance of IC and SF models on classes not seen at training time in ultra low resource scenarios. We establish a few-shot IC/SF benchmark by defining few-shot splits for three public IC/SF datasets, ATIS, TOP, and Snips. We show that two popular few-shot learning algorithms, model agnostic meta learning (MAML) and prototypical networks, outperform a fine-tuning baseline on this benchmark. Prototypical networks achieves significant gains in IC performance on the ATIS and TOP datasets, while both prototypical networks and MAML outperform the baseline with respect to SF on all three datasets. In addition, we demonstrate that joint training as well as the use of pre-trained language models, ELMo and BERT in our case, are complementary to these few-shot learning methods and yield further gains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krone-etal-2020-learning">
<titleInfo>
<title>Learning to Classify Intents and Slot Labels Given a Handful of Examples</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Krone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihail</namePart>
<namePart type="family">Eric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iñigo</namePart>
<namePart type="family">Casanueva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rushin</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Intent classification (IC) and slot filling (SF) are core components in most goal-oriented dialogue systems. Current IC/SF models perform poorly when the number of training examples per class is small. We propose a new few-shot learning task, few-shot IC/SF, to study and improve the performance of IC and SF models on classes not seen at training time in ultra low resource scenarios. We establish a few-shot IC/SF benchmark by defining few-shot splits for three public IC/SF datasets, ATIS, TOP, and Snips. We show that two popular few-shot learning algorithms, model agnostic meta learning (MAML) and prototypical networks, outperform a fine-tuning baseline on this benchmark. Prototypical networks achieves significant gains in IC performance on the ATIS and TOP datasets, while both prototypical networks and MAML outperform the baseline with respect to SF on all three datasets. In addition, we demonstrate that joint training as well as the use of pre-trained language models, ELMo and BERT in our case, are complementary to these few-shot learning methods and yield further gains.</abstract>
<identifier type="citekey">krone-etal-2020-learning</identifier>
<identifier type="doi">10.18653/v1/2020.nlp4convai-1.12</identifier>
<location>
<url>https://aclanthology.org/2020.nlp4convai-1.12</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>96</start>
<end>108</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Classify Intents and Slot Labels Given a Handful of Examples
%A Krone, Jason
%A Zhang, Yi
%A Diab, Mona
%Y Wen, Tsung-Hsien
%Y Celikyilmaz, Asli
%Y Yu, Zhou
%Y Papangelis, Alexandros
%Y Eric, Mihail
%Y Kumar, Anuj
%Y Casanueva, Iñigo
%Y Shah, Rushin
%S Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F krone-etal-2020-learning
%X Intent classification (IC) and slot filling (SF) are core components in most goal-oriented dialogue systems. Current IC/SF models perform poorly when the number of training examples per class is small. We propose a new few-shot learning task, few-shot IC/SF, to study and improve the performance of IC and SF models on classes not seen at training time in ultra low resource scenarios. We establish a few-shot IC/SF benchmark by defining few-shot splits for three public IC/SF datasets, ATIS, TOP, and Snips. We show that two popular few-shot learning algorithms, model agnostic meta learning (MAML) and prototypical networks, outperform a fine-tuning baseline on this benchmark. Prototypical networks achieves significant gains in IC performance on the ATIS and TOP datasets, while both prototypical networks and MAML outperform the baseline with respect to SF on all three datasets. In addition, we demonstrate that joint training as well as the use of pre-trained language models, ELMo and BERT in our case, are complementary to these few-shot learning methods and yield further gains.
%R 10.18653/v1/2020.nlp4convai-1.12
%U https://aclanthology.org/2020.nlp4convai-1.12
%U https://doi.org/10.18653/v1/2020.nlp4convai-1.12
%P 96-108
Markdown (Informal)
[Learning to Classify Intents and Slot Labels Given a Handful of Examples](https://aclanthology.org/2020.nlp4convai-1.12) (Krone et al., NLP4ConvAI 2020)
ACL