@inproceedings{dey-desarkar-2023-dial,
title = "Dial-{M}: A Masking-based Framework for Dialogue Evaluation",
author = "Dey, Suvodip and
Desarkar, Maunendra Sankar",
editor = "Stoyanchev, Svetlana and
Joty, Shafiq and
Schlangen, David and
Dusek, Ondrej and
Kennington, Casey and
Alikhani, Malihe",
booktitle = "Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2023",
address = "Prague, Czechia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigdial-1.7",
doi = "10.18653/v1/2023.sigdial-1.7",
pages = "77--84",
abstract = "In dialogue systems, automatically evaluating machine-generated responses is critical and challenging. Despite the tremendous progress in dialogue generation research, its evaluation heavily depends on human judgments. The standard word-overlapping based evaluation metrics are ineffective for dialogues. As a result, most of the recently proposed metrics are model-based and reference-free, which learn to score different aspects of a conversation. However, understanding each aspect requires a separate model, which makes them computationally expensive. To this end, we propose Dial-M, a Masking-based reference-free framework for Dialogue evaluation. The main idea is to mask the keywords of the current utterance and predict them, given the dialogue history and various conditions (like knowledge, persona, etc.), thereby making the evaluation framework simple and easily extensible for multiple datasets. Regardless of its simplicity, Dial-M achieves comparable performance to state-of-the-art metrics on several dialogue evaluation datasets. We also discuss the interpretability of our proposed metric along with error analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dey-desarkar-2023-dial">
<titleInfo>
<title>Dial-M: A Masking-based Framework for Dialogue Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Suvodip</namePart>
<namePart type="family">Dey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maunendra</namePart>
<namePart type="given">Sankar</namePart>
<namePart type="family">Desarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Stoyanchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Dusek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Casey</namePart>
<namePart type="family">Kennington</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czechia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In dialogue systems, automatically evaluating machine-generated responses is critical and challenging. Despite the tremendous progress in dialogue generation research, its evaluation heavily depends on human judgments. The standard word-overlapping based evaluation metrics are ineffective for dialogues. As a result, most of the recently proposed metrics are model-based and reference-free, which learn to score different aspects of a conversation. However, understanding each aspect requires a separate model, which makes them computationally expensive. To this end, we propose Dial-M, a Masking-based reference-free framework for Dialogue evaluation. The main idea is to mask the keywords of the current utterance and predict them, given the dialogue history and various conditions (like knowledge, persona, etc.), thereby making the evaluation framework simple and easily extensible for multiple datasets. Regardless of its simplicity, Dial-M achieves comparable performance to state-of-the-art metrics on several dialogue evaluation datasets. We also discuss the interpretability of our proposed metric along with error analysis.</abstract>
<identifier type="citekey">dey-desarkar-2023-dial</identifier>
<identifier type="doi">10.18653/v1/2023.sigdial-1.7</identifier>
<location>
<url>https://aclanthology.org/2023.sigdial-1.7</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>77</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dial-M: A Masking-based Framework for Dialogue Evaluation
%A Dey, Suvodip
%A Desarkar, Maunendra Sankar
%Y Stoyanchev, Svetlana
%Y Joty, Shafiq
%Y Schlangen, David
%Y Dusek, Ondrej
%Y Kennington, Casey
%Y Alikhani, Malihe
%S Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czechia
%F dey-desarkar-2023-dial
%X In dialogue systems, automatically evaluating machine-generated responses is critical and challenging. Despite the tremendous progress in dialogue generation research, its evaluation heavily depends on human judgments. The standard word-overlapping based evaluation metrics are ineffective for dialogues. As a result, most of the recently proposed metrics are model-based and reference-free, which learn to score different aspects of a conversation. However, understanding each aspect requires a separate model, which makes them computationally expensive. To this end, we propose Dial-M, a Masking-based reference-free framework for Dialogue evaluation. The main idea is to mask the keywords of the current utterance and predict them, given the dialogue history and various conditions (like knowledge, persona, etc.), thereby making the evaluation framework simple and easily extensible for multiple datasets. Regardless of its simplicity, Dial-M achieves comparable performance to state-of-the-art metrics on several dialogue evaluation datasets. We also discuss the interpretability of our proposed metric along with error analysis.
%R 10.18653/v1/2023.sigdial-1.7
%U https://aclanthology.org/2023.sigdial-1.7
%U https://doi.org/10.18653/v1/2023.sigdial-1.7
%P 77-84
Markdown (Informal)
[Dial-M: A Masking-based Framework for Dialogue Evaluation](https://aclanthology.org/2023.sigdial-1.7) (Dey & Desarkar, SIGDIAL 2023)
ACL