@inproceedings{mehri-eskenazi-2021-schema,
title = "Schema-Guided Paradigm for Zero-Shot Dialog",
author = "Mehri, Shikib and
Eskenazi, Maxine",
booktitle = "Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = jul,
year = "2021",
address = "Singapore and Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigdial-1.52",
pages = "499--508",
abstract = "Developing mechanisms that flexibly adapt dialog systems to unseen tasks and domains is a major challenge in dialog research. Neural models implicitly memorize task-specific dialog policies from the training data. We posit that this implicit memorization has precluded zero-shot transfer learning. To this end, we leverage the schema-guided paradigm, wherein the task-specific dialog policy is explicitly provided to the model. We introduce the Schema Attention Model (SAM) and improved schema representations for the STAR corpus. SAM obtains significant improvement in zero-shot settings, with a +22 F1 score improvement over prior work. These results validate the feasibility of zero-shot generalizability in dialog. Ablation experiments are also presented to demonstrate the efficacy of SAM.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mehri-eskenazi-2021-schema">
<titleInfo>
<title>Schema-Guided Paradigm for Zero-Shot Dialog</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shikib</namePart>
<namePart type="family">Mehri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxine</namePart>
<namePart type="family">Eskenazi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jul</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore and Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Developing mechanisms that flexibly adapt dialog systems to unseen tasks and domains is a major challenge in dialog research. Neural models implicitly memorize task-specific dialog policies from the training data. We posit that this implicit memorization has precluded zero-shot transfer learning. To this end, we leverage the schema-guided paradigm, wherein the task-specific dialog policy is explicitly provided to the model. We introduce the Schema Attention Model (SAM) and improved schema representations for the STAR corpus. SAM obtains significant improvement in zero-shot settings, with a +22 F1 score improvement over prior work. These results validate the feasibility of zero-shot generalizability in dialog. Ablation experiments are also presented to demonstrate the efficacy of SAM.</abstract>
<identifier type="citekey">mehri-eskenazi-2021-schema</identifier>
<location>
<url>https://aclanthology.org/2021.sigdial-1.52</url>
</location>
<part>
<date>2021-jul</date>
<extent unit="page">
<start>499</start>
<end>508</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Schema-Guided Paradigm for Zero-Shot Dialog
%A Mehri, Shikib
%A Eskenazi, Maxine
%S Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2021
%8 jul
%I Association for Computational Linguistics
%C Singapore and Online
%F mehri-eskenazi-2021-schema
%X Developing mechanisms that flexibly adapt dialog systems to unseen tasks and domains is a major challenge in dialog research. Neural models implicitly memorize task-specific dialog policies from the training data. We posit that this implicit memorization has precluded zero-shot transfer learning. To this end, we leverage the schema-guided paradigm, wherein the task-specific dialog policy is explicitly provided to the model. We introduce the Schema Attention Model (SAM) and improved schema representations for the STAR corpus. SAM obtains significant improvement in zero-shot settings, with a +22 F1 score improvement over prior work. These results validate the feasibility of zero-shot generalizability in dialog. Ablation experiments are also presented to demonstrate the efficacy of SAM.
%U https://aclanthology.org/2021.sigdial-1.52
%P 499-508
Markdown (Informal)
[Schema-Guided Paradigm for Zero-Shot Dialog](https://aclanthology.org/2021.sigdial-1.52) (Mehri & Eskenazi, SIGDIAL 2021)
ACL
- Shikib Mehri and Maxine Eskenazi. 2021. Schema-Guided Paradigm for Zero-Shot Dialog. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 499–508, Singapore and Online. Association for Computational Linguistics.