@inproceedings{grover-etal-2021-mrf,
title = "{MRF}-Chat: Improving Dialogue with {M}arkov Random Fields",
author = "Grover, Ishaan and
Huggins, Matthew and
Breazeal, Cynthia and
Park, Hae Won",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.403",
doi = "10.18653/v1/2021.emnlp-main.403",
pages = "4925--4936",
abstract = "Recent state-of-the-art approaches in open-domain dialogue include training end-to-end deep-learning models to learn various conversational features like emotional content of response, symbolic transitions of dialogue contexts in a knowledge graph and persona of the agent and the user, among others. While neural models have shown reasonable results, modelling the cognitive processes that humans use when conversing with each other may improve the agent{'}s quality of responses. A key element of natural conversation is to tailor one{'}s response such that it accounts for concepts that the speaker and listener may or may not know and the contextual relevance of all prior concepts used in conversation. We show that a rich representation and explicit modeling of these psychological processes can improve predictions made by existing neural network models. In this work, we propose a novel probabilistic approach using Markov Random Fields (MRF) to augment existing deep-learning methods for improved next utterance prediction. Using human and automatic evaluations, we show that our augmentation approach significantly improves the performance of existing state-of-the-art retrieval models for open-domain conversational agents.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grover-etal-2021-mrf">
<titleInfo>
<title>MRF-Chat: Improving Dialogue with Markov Random Fields</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ishaan</namePart>
<namePart type="family">Grover</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Huggins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cynthia</namePart>
<namePart type="family">Breazeal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hae</namePart>
<namePart type="given">Won</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent state-of-the-art approaches in open-domain dialogue include training end-to-end deep-learning models to learn various conversational features like emotional content of response, symbolic transitions of dialogue contexts in a knowledge graph and persona of the agent and the user, among others. While neural models have shown reasonable results, modelling the cognitive processes that humans use when conversing with each other may improve the agent’s quality of responses. A key element of natural conversation is to tailor one’s response such that it accounts for concepts that the speaker and listener may or may not know and the contextual relevance of all prior concepts used in conversation. We show that a rich representation and explicit modeling of these psychological processes can improve predictions made by existing neural network models. In this work, we propose a novel probabilistic approach using Markov Random Fields (MRF) to augment existing deep-learning methods for improved next utterance prediction. Using human and automatic evaluations, we show that our augmentation approach significantly improves the performance of existing state-of-the-art retrieval models for open-domain conversational agents.</abstract>
<identifier type="citekey">grover-etal-2021-mrf</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.403</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.403</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4925</start>
<end>4936</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MRF-Chat: Improving Dialogue with Markov Random Fields
%A Grover, Ishaan
%A Huggins, Matthew
%A Breazeal, Cynthia
%A Park, Hae Won
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F grover-etal-2021-mrf
%X Recent state-of-the-art approaches in open-domain dialogue include training end-to-end deep-learning models to learn various conversational features like emotional content of response, symbolic transitions of dialogue contexts in a knowledge graph and persona of the agent and the user, among others. While neural models have shown reasonable results, modelling the cognitive processes that humans use when conversing with each other may improve the agent’s quality of responses. A key element of natural conversation is to tailor one’s response such that it accounts for concepts that the speaker and listener may or may not know and the contextual relevance of all prior concepts used in conversation. We show that a rich representation and explicit modeling of these psychological processes can improve predictions made by existing neural network models. In this work, we propose a novel probabilistic approach using Markov Random Fields (MRF) to augment existing deep-learning methods for improved next utterance prediction. Using human and automatic evaluations, we show that our augmentation approach significantly improves the performance of existing state-of-the-art retrieval models for open-domain conversational agents.
%R 10.18653/v1/2021.emnlp-main.403
%U https://aclanthology.org/2021.emnlp-main.403
%U https://doi.org/10.18653/v1/2021.emnlp-main.403
%P 4925-4936
Markdown (Informal)
[MRF-Chat: Improving Dialogue with Markov Random Fields](https://aclanthology.org/2021.emnlp-main.403) (Grover et al., EMNLP 2021)
ACL
- Ishaan Grover, Matthew Huggins, Cynthia Breazeal, and Hae Won Park. 2021. MRF-Chat: Improving Dialogue with Markov Random Fields. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4925–4936, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.