@inproceedings{zeng-etal-2022-semantic,
title = "Semantic Content Prediction for Generating Interviewing Dialogues to Elicit Users{'} Food Preferences",
author = "Zeng, Jie and
Sakato, Tatsuya and
Nakano, Yukiko",
editor = "Wu, Xianchao and
Ruan, Peiying and
Li, Sheng and
Dong, Yi",
booktitle = "Proceedings of the Second Workshop on When Creative AI Meets Conversational AI",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.cai-1.7",
pages = "48--58",
abstract = "Dialogue systems that aim to acquire user models through interactions with users need to have interviewing functionality. In this study, we propose a method to generate interview dialogues to build a dialogue system that acquires user preferences for food. First, we collected 118 text-based dialogues between the interviewer and customer and annotated the communicative function and semantic content of the utterances. Next, using the corpus as training data, we created a classification model for the communicative function of the interviewer{'}s next utterance and a generative model that predicts the semantic content of the utterance based on the dialogue history. By representing semantic content as a sequence of tokens, we evaluated the semantic content prediction model using BLEU. The results demonstrated that the semantic content produced by the proposed method was closer to the ground truth than the semantic content transformed from the output text generated by the retrieval model and GPT-2. Further, we present some examples of dialogue generation by applying model outputs to template-based sentence generation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2022-semantic">
<titleInfo>
<title>Semantic Content Prediction for Generating Interviewing Dialogues to Elicit Users’ Food Preferences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Sakato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yukiko</namePart>
<namePart type="family">Nakano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on When Creative AI Meets Conversational AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xianchao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peiying</namePart>
<namePart type="family">Ruan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialogue systems that aim to acquire user models through interactions with users need to have interviewing functionality. In this study, we propose a method to generate interview dialogues to build a dialogue system that acquires user preferences for food. First, we collected 118 text-based dialogues between the interviewer and customer and annotated the communicative function and semantic content of the utterances. Next, using the corpus as training data, we created a classification model for the communicative function of the interviewer’s next utterance and a generative model that predicts the semantic content of the utterance based on the dialogue history. By representing semantic content as a sequence of tokens, we evaluated the semantic content prediction model using BLEU. The results demonstrated that the semantic content produced by the proposed method was closer to the ground truth than the semantic content transformed from the output text generated by the retrieval model and GPT-2. Further, we present some examples of dialogue generation by applying model outputs to template-based sentence generation.</abstract>
<identifier type="citekey">zeng-etal-2022-semantic</identifier>
<location>
<url>https://aclanthology.org/2022.cai-1.7</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>48</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic Content Prediction for Generating Interviewing Dialogues to Elicit Users’ Food Preferences
%A Zeng, Jie
%A Sakato, Tatsuya
%A Nakano, Yukiko
%Y Wu, Xianchao
%Y Ruan, Peiying
%Y Li, Sheng
%Y Dong, Yi
%S Proceedings of the Second Workshop on When Creative AI Meets Conversational AI
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F zeng-etal-2022-semantic
%X Dialogue systems that aim to acquire user models through interactions with users need to have interviewing functionality. In this study, we propose a method to generate interview dialogues to build a dialogue system that acquires user preferences for food. First, we collected 118 text-based dialogues between the interviewer and customer and annotated the communicative function and semantic content of the utterances. Next, using the corpus as training data, we created a classification model for the communicative function of the interviewer’s next utterance and a generative model that predicts the semantic content of the utterance based on the dialogue history. By representing semantic content as a sequence of tokens, we evaluated the semantic content prediction model using BLEU. The results demonstrated that the semantic content produced by the proposed method was closer to the ground truth than the semantic content transformed from the output text generated by the retrieval model and GPT-2. Further, we present some examples of dialogue generation by applying model outputs to template-based sentence generation.
%U https://aclanthology.org/2022.cai-1.7
%P 48-58
Markdown (Informal)
[Semantic Content Prediction for Generating Interviewing Dialogues to Elicit Users’ Food Preferences](https://aclanthology.org/2022.cai-1.7) (Zeng et al., CAI 2022)
ACL