@inproceedings{jin-etal-2021-assistance,
title = "Can {I} Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling",
author = "Jin, Di and
Kim, Seokhwan and
Hakkani-Tur, Dilek",
booktitle = "Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.dialdoc-1.16",
doi = "10.18653/v1/2021.dialdoc-1.16",
pages = "119--127",
abstract = "Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs. However, users oftentimes have requests that are out of the scope of these APIs. This work focuses on responding to these beyond-API-coverage user turns by incorporating external, unstructured knowledge sources. Our approach works in a pipelined manner with knowledge-seeking turn detection, knowledge selection, and response generation in sequence. We introduce novel data augmentation methods for the first two steps and demonstrate that the use of information extracted from dialogue context improves the knowledge selection and end-to-end performances. Through experiments, we achieve state-of-the-art performance for both automatic and human evaluation metrics on the DSTC9 Track 1 benchmark dataset, validating the effectiveness of our contributions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2021-assistance">
<titleInfo>
<title>Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</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 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs. However, users oftentimes have requests that are out of the scope of these APIs. This work focuses on responding to these beyond-API-coverage user turns by incorporating external, unstructured knowledge sources. Our approach works in a pipelined manner with knowledge-seeking turn detection, knowledge selection, and response generation in sequence. We introduce novel data augmentation methods for the first two steps and demonstrate that the use of information extracted from dialogue context improves the knowledge selection and end-to-end performances. Through experiments, we achieve state-of-the-art performance for both automatic and human evaluation metrics on the DSTC9 Track 1 benchmark dataset, validating the effectiveness of our contributions.</abstract>
<identifier type="citekey">jin-etal-2021-assistance</identifier>
<identifier type="doi">10.18653/v1/2021.dialdoc-1.16</identifier>
<location>
<url>https://aclanthology.org/2021.dialdoc-1.16</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>119</start>
<end>127</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling
%A Jin, Di
%A Kim, Seokhwan
%A Hakkani-Tur, Dilek
%S Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F jin-etal-2021-assistance
%X Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs. However, users oftentimes have requests that are out of the scope of these APIs. This work focuses on responding to these beyond-API-coverage user turns by incorporating external, unstructured knowledge sources. Our approach works in a pipelined manner with knowledge-seeking turn detection, knowledge selection, and response generation in sequence. We introduce novel data augmentation methods for the first two steps and demonstrate that the use of information extracted from dialogue context improves the knowledge selection and end-to-end performances. Through experiments, we achieve state-of-the-art performance for both automatic and human evaluation metrics on the DSTC9 Track 1 benchmark dataset, validating the effectiveness of our contributions.
%R 10.18653/v1/2021.dialdoc-1.16
%U https://aclanthology.org/2021.dialdoc-1.16
%U https://doi.org/10.18653/v1/2021.dialdoc-1.16
%P 119-127
Markdown (Informal)
[Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling](https://aclanthology.org/2021.dialdoc-1.16) (Jin et al., dialdoc 2021)
ACL