@inproceedings{hu-etal-2022-context,
title = "In-Context Learning for Few-Shot Dialogue State Tracking",
author = "Hu, Yushi and
Lee, Chia-Hsuan and
Xie, Tianbao and
Yu, Tao and
Smith, Noah A. and
Ostendorf, Mari",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.193/",
doi = "10.18653/v1/2022.findings-emnlp.193",
pages = "2627--2643",
abstract = "Collecting and annotating task-oriented dialogues is time-consuming and costly. Thus, zero and few shot learning for dialogue tasks presents an exciting opportunity. In this work, we propose an in-context (IC) learning framework for zero-shot and few-shot learning dialogue state tracking (DST), where a large pretrained language model (LM) takes a test instance and a few exemplars as input, and directly decodes the dialogue state without any parameter updates. This approach is more flexible and scalable than prior DST work when adapting to new domains and scenarios. To better leverage a tabular domain description in the LM prompt, we reformulate DST into a text-to-SQL problem. We also propose a novel approach to retrieve annotated dialogues as exemplars. Empirical results on MultiWOZ show that our method IC-DST substantially outperforms previous fine-tuned state-of-the-art models in few-shot settings. In addition, we test IC-DST in zero-shot settings, in which the model only takes a fixed task instruction as input, finding that it outperforms previous zero-shot methods by a large margin."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2022-context">
<titleInfo>
<title>In-Context Learning for Few-Shot Dialogue State Tracking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yushi</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-Hsuan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianbao</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mari</namePart>
<namePart type="family">Ostendorf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Collecting and annotating task-oriented dialogues is time-consuming and costly. Thus, zero and few shot learning for dialogue tasks presents an exciting opportunity. In this work, we propose an in-context (IC) learning framework for zero-shot and few-shot learning dialogue state tracking (DST), where a large pretrained language model (LM) takes a test instance and a few exemplars as input, and directly decodes the dialogue state without any parameter updates. This approach is more flexible and scalable than prior DST work when adapting to new domains and scenarios. To better leverage a tabular domain description in the LM prompt, we reformulate DST into a text-to-SQL problem. We also propose a novel approach to retrieve annotated dialogues as exemplars. Empirical results on MultiWOZ show that our method IC-DST substantially outperforms previous fine-tuned state-of-the-art models in few-shot settings. In addition, we test IC-DST in zero-shot settings, in which the model only takes a fixed task instruction as input, finding that it outperforms previous zero-shot methods by a large margin.</abstract>
<identifier type="citekey">hu-etal-2022-context</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.193</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.193/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>2627</start>
<end>2643</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T In-Context Learning for Few-Shot Dialogue State Tracking
%A Hu, Yushi
%A Lee, Chia-Hsuan
%A Xie, Tianbao
%A Yu, Tao
%A Smith, Noah A.
%A Ostendorf, Mari
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F hu-etal-2022-context
%X Collecting and annotating task-oriented dialogues is time-consuming and costly. Thus, zero and few shot learning for dialogue tasks presents an exciting opportunity. In this work, we propose an in-context (IC) learning framework for zero-shot and few-shot learning dialogue state tracking (DST), where a large pretrained language model (LM) takes a test instance and a few exemplars as input, and directly decodes the dialogue state without any parameter updates. This approach is more flexible and scalable than prior DST work when adapting to new domains and scenarios. To better leverage a tabular domain description in the LM prompt, we reformulate DST into a text-to-SQL problem. We also propose a novel approach to retrieve annotated dialogues as exemplars. Empirical results on MultiWOZ show that our method IC-DST substantially outperforms previous fine-tuned state-of-the-art models in few-shot settings. In addition, we test IC-DST in zero-shot settings, in which the model only takes a fixed task instruction as input, finding that it outperforms previous zero-shot methods by a large margin.
%R 10.18653/v1/2022.findings-emnlp.193
%U https://aclanthology.org/2022.findings-emnlp.193/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.193
%P 2627-2643
Markdown (Informal)
[In-Context Learning for Few-Shot Dialogue State Tracking](https://aclanthology.org/2022.findings-emnlp.193/) (Hu et al., Findings 2022)
ACL
- Yushi Hu, Chia-Hsuan Lee, Tianbao Xie, Tao Yu, Noah A. Smith, and Mari Ostendorf. 2022. In-Context Learning for Few-Shot Dialogue State Tracking. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2627–2643, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.