@inproceedings{du-etal-2021-qa,
title = "{QA}-Driven Zero-shot Slot Filling with Weak Supervision Pretraining",
author = "Du, Xinya and
He, Luheng and
Li, Qi and
Yu, Dian and
Pasupat, Panupong and
Zhang, Yuan",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.83/",
doi = "10.18653/v1/2021.acl-short.83",
pages = "654--664",
abstract = "Slot-filling is an essential component for building task-oriented dialog systems. In this work, we focus on the zero-shot slot-filling problem, where the model needs to predict slots and their values, given utterances from new domains without training on the target domain. Prior methods directly encode slot descriptions to generalize to unseen slot types. However, raw slot descriptions are often ambiguous and do not encode enough semantic information, limiting the models' zero-shot capability. To address this problem, we introduce QA-driven slot filling (QASF), which extracts slot-filler spans from utterances with a span-based QA model. We use a linguistically motivated questioning strategy to turn descriptions into questions, allowing the model to generalize to unseen slot types. Moreover, our QASF model can benefit from weak supervision signals from QA pairs synthetically generated from unlabeled conversations. Our full system substantially outperforms baselines by over 5{\%} on the SNIPS benchmark."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="du-etal-2021-qa">
<titleInfo>
<title>QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinya</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luheng</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dian</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Panupong</namePart>
<namePart type="family">Pasupat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Slot-filling is an essential component for building task-oriented dialog systems. In this work, we focus on the zero-shot slot-filling problem, where the model needs to predict slots and their values, given utterances from new domains without training on the target domain. Prior methods directly encode slot descriptions to generalize to unseen slot types. However, raw slot descriptions are often ambiguous and do not encode enough semantic information, limiting the models’ zero-shot capability. To address this problem, we introduce QA-driven slot filling (QASF), which extracts slot-filler spans from utterances with a span-based QA model. We use a linguistically motivated questioning strategy to turn descriptions into questions, allowing the model to generalize to unseen slot types. Moreover, our QASF model can benefit from weak supervision signals from QA pairs synthetically generated from unlabeled conversations. Our full system substantially outperforms baselines by over 5% on the SNIPS benchmark.</abstract>
<identifier type="citekey">du-etal-2021-qa</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.83</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.83/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>654</start>
<end>664</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining
%A Du, Xinya
%A He, Luheng
%A Li, Qi
%A Yu, Dian
%A Pasupat, Panupong
%A Zhang, Yuan
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F du-etal-2021-qa
%X Slot-filling is an essential component for building task-oriented dialog systems. In this work, we focus on the zero-shot slot-filling problem, where the model needs to predict slots and their values, given utterances from new domains without training on the target domain. Prior methods directly encode slot descriptions to generalize to unseen slot types. However, raw slot descriptions are often ambiguous and do not encode enough semantic information, limiting the models’ zero-shot capability. To address this problem, we introduce QA-driven slot filling (QASF), which extracts slot-filler spans from utterances with a span-based QA model. We use a linguistically motivated questioning strategy to turn descriptions into questions, allowing the model to generalize to unseen slot types. Moreover, our QASF model can benefit from weak supervision signals from QA pairs synthetically generated from unlabeled conversations. Our full system substantially outperforms baselines by over 5% on the SNIPS benchmark.
%R 10.18653/v1/2021.acl-short.83
%U https://aclanthology.org/2021.acl-short.83/
%U https://doi.org/10.18653/v1/2021.acl-short.83
%P 654-664
Markdown (Informal)
[QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining](https://aclanthology.org/2021.acl-short.83/) (Du et al., ACL-IJCNLP 2021)
ACL
- Xinya Du, Luheng He, Qi Li, Dian Yu, Panupong Pasupat, and Yuan Zhang. 2021. QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 654–664, Online. Association for Computational Linguistics.