<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gul-artzi-2024-cogen">
    <titleInfo>
        <title>CoGen: Learning from Feedback with Coupled Comprehension and Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mustafa</namePart>
        <namePart type="given">Omer</namePart>
        <namePart type="family">Gul</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yoav</namePart>
        <namePart type="family">Artzi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Systems with both language comprehension and generation capabilities can benefit from the tight connection between the two. This work studies coupling comprehension and generation with focus on continually learning from interaction with users. We propose techniques to tightly integrate the two capabilities for both learning and inference. We situate our studies in two-player reference games, and deploy various models for thousands of interactions with human users, while learning from interaction feedback signals. We show dramatic improvements in performance over time, with comprehension-generation coupling leading to performance improvements up to 26% in absolute terms and up to 17% higher accuracies compared to a non-coupled system. Our analysis also shows coupling has substantial qualitative impact on the system’s language, making it significantly more human-like.</abstract>
    <identifier type="citekey">gul-artzi-2024-cogen</identifier>
    <identifier type="doi">10.18653/v1/2024.emnlp-main.721</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.721</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>12966</start>
            <end>12982</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CoGen: Learning from Feedback with Coupled Comprehension and Generation
%A Gul, Mustafa Omer
%A Artzi, Yoav
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F gul-artzi-2024-cogen
%X Systems with both language comprehension and generation capabilities can benefit from the tight connection between the two. This work studies coupling comprehension and generation with focus on continually learning from interaction with users. We propose techniques to tightly integrate the two capabilities for both learning and inference. We situate our studies in two-player reference games, and deploy various models for thousands of interactions with human users, while learning from interaction feedback signals. We show dramatic improvements in performance over time, with comprehension-generation coupling leading to performance improvements up to 26% in absolute terms and up to 17% higher accuracies compared to a non-coupled system. Our analysis also shows coupling has substantial qualitative impact on the system’s language, making it significantly more human-like.
%R 10.18653/v1/2024.emnlp-main.721
%U https://aclanthology.org/2024.emnlp-main.721
%U https://doi.org/10.18653/v1/2024.emnlp-main.721
%P 12966-12982

Markdown (Informal)

[CoGen: Learning from Feedback with Coupled Comprehension and Generation](https://aclanthology.org/2024.emnlp-main.721) (Gul & Artzi, EMNLP 2024)

• CoGen: Learning from Feedback with Coupled Comprehension and Generation (Gul & Artzi, EMNLP 2024)

ACL

• Mustafa Omer Gul and Yoav Artzi. 2024. CoGen: Learning from Feedback with Coupled Comprehension and Generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12966–12982, Miami, Florida, USA. Association for Computational Linguistics.