@inproceedings{kim-etal-2021-document,
title = "Document-Grounded Goal-Oriented Dialogue Systems on Pre-Trained Language Model with Diverse Input Representation",
author = "Kim, Boeun and
Lee, Dohaeng and
Kim, Sihyung and
Lee, Yejin and
Huang, Jin-Xia and
Kwon, Oh-Woog and
Kim, Harksoo",
editor = "Feng, Song and
Reddy, Siva and
Alikhani, Malihe and
He, He and
Ji, Yangfeng and
Iyyer, Mohit and
Yu, Zhou",
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-1.12",
doi = "10.18653/v1/2021.dialdoc-1.12",
pages = "98--102",
abstract = "Document-grounded goal-oriented dialog system understands users{'} utterances, and generates proper responses by using information obtained from documents. The Dialdoc21 shared task consists of two subtasks; subtask1, finding text spans associated with users{'} utterances from documents, and subtask2, generating responses based on information obtained from subtask1. In this paper, we propose two models (i.e., a knowledge span prediction model and a response generation model) for the subtask1 and the subtask2. In the subtask1, dialogue act losses are used with RoBERTa, and title embeddings are added to input representation of RoBERTa. In the subtask2, various special tokens and embeddings are added to input representation of BART{'}s encoder. Then, we propose a method to assign different difficulty scores to leverage curriculum learning. In the subtask1, our span prediction model achieved F1-scores of 74.81 (ranked at top 7) and 73.41 (ranked at top 5) in test-dev phase and test phase, respectively. In the subtask2, our response generation model achieved sacreBLEUs of 37.50 (ranked at top 3) and 41.06 (ranked at top 1) in in test-dev phase and test phase, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2021-document">
<titleInfo>
<title>Document-Grounded Goal-Oriented Dialogue Systems on Pre-Trained Language Model with Diverse Input Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boeun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dohaeng</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sihyung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yejin</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin-Xia</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oh-Woog</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harksoo</namePart>
<namePart type="family">Kim</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>
<name type="personal">
<namePart type="given">Song</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siva</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangfeng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Iyyer</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Document-grounded goal-oriented dialog system understands users’ utterances, and generates proper responses by using information obtained from documents. The Dialdoc21 shared task consists of two subtasks; subtask1, finding text spans associated with users’ utterances from documents, and subtask2, generating responses based on information obtained from subtask1. In this paper, we propose two models (i.e., a knowledge span prediction model and a response generation model) for the subtask1 and the subtask2. In the subtask1, dialogue act losses are used with RoBERTa, and title embeddings are added to input representation of RoBERTa. In the subtask2, various special tokens and embeddings are added to input representation of BART’s encoder. Then, we propose a method to assign different difficulty scores to leverage curriculum learning. In the subtask1, our span prediction model achieved F1-scores of 74.81 (ranked at top 7) and 73.41 (ranked at top 5) in test-dev phase and test phase, respectively. In the subtask2, our response generation model achieved sacreBLEUs of 37.50 (ranked at top 3) and 41.06 (ranked at top 1) in in test-dev phase and test phase, respectively.</abstract>
<identifier type="citekey">kim-etal-2021-document</identifier>
<identifier type="doi">10.18653/v1/2021.dialdoc-1.12</identifier>
<location>
<url>https://aclanthology.org/2021.dialdoc-1.12</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>98</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document-Grounded Goal-Oriented Dialogue Systems on Pre-Trained Language Model with Diverse Input Representation
%A Kim, Boeun
%A Lee, Dohaeng
%A Kim, Sihyung
%A Lee, Yejin
%A Huang, Jin-Xia
%A Kwon, Oh-Woog
%A Kim, Harksoo
%Y Feng, Song
%Y Reddy, Siva
%Y Alikhani, Malihe
%Y He, He
%Y Ji, Yangfeng
%Y Iyyer, Mohit
%Y Yu, Zhou
%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 kim-etal-2021-document
%X Document-grounded goal-oriented dialog system understands users’ utterances, and generates proper responses by using information obtained from documents. The Dialdoc21 shared task consists of two subtasks; subtask1, finding text spans associated with users’ utterances from documents, and subtask2, generating responses based on information obtained from subtask1. In this paper, we propose two models (i.e., a knowledge span prediction model and a response generation model) for the subtask1 and the subtask2. In the subtask1, dialogue act losses are used with RoBERTa, and title embeddings are added to input representation of RoBERTa. In the subtask2, various special tokens and embeddings are added to input representation of BART’s encoder. Then, we propose a method to assign different difficulty scores to leverage curriculum learning. In the subtask1, our span prediction model achieved F1-scores of 74.81 (ranked at top 7) and 73.41 (ranked at top 5) in test-dev phase and test phase, respectively. In the subtask2, our response generation model achieved sacreBLEUs of 37.50 (ranked at top 3) and 41.06 (ranked at top 1) in in test-dev phase and test phase, respectively.
%R 10.18653/v1/2021.dialdoc-1.12
%U https://aclanthology.org/2021.dialdoc-1.12
%U https://doi.org/10.18653/v1/2021.dialdoc-1.12
%P 98-102
Markdown (Informal)
[Document-Grounded Goal-Oriented Dialogue Systems on Pre-Trained Language Model with Diverse Input Representation](https://aclanthology.org/2021.dialdoc-1.12) (Kim et al., dialdoc 2021)
ACL