<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-templm">
    <titleInfo>
        <title>TempLM: Distilling Language Models into Template-Based Generators</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tianyi</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mina</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiang</namePart>
        <namePart type="given">Lisa</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ende</namePart>
        <namePart type="family">Shen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tatsunori</namePart>
        <namePart type="family">Hashimoto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>While pretrained language models (PLMs) have greatly improved text generation, they have also been known to produce unfaithful or inappropriate content. In contrast, classic template-based systems provide strong guarantees of faithfulness at the cost of fluency. We propose TempLM, which achieves the best of both worlds by distilling a PLM into a template-based generator. On the E2E and SynthBio data-to-text datasets, we show that TempLM is more faithful than the original PLM and is more fluent than prior template systems. Notably, on an out-of-domain evaluation, TempLM reduces a finetuned BART model’s unfaithfulness rate from 83% to 0%. In a human study, we find that TempLM’s templates substantially improve upon human-written ones in BERTScore.</abstract>
    <identifier type="citekey">zhang-etal-2023-templm</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.124</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.124</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>1970</start>
            <end>1994</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TempLM: Distilling Language Models into Template-Based Generators
%A Zhang, Tianyi
%A Lee, Mina
%A Li, Xiang Lisa
%A Shen, Ende
%A Hashimoto, Tatsunori
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zhang-etal-2023-templm
%X While pretrained language models (PLMs) have greatly improved text generation, they have also been known to produce unfaithful or inappropriate content. In contrast, classic template-based systems provide strong guarantees of faithfulness at the cost of fluency. We propose TempLM, which achieves the best of both worlds by distilling a PLM into a template-based generator. On the E2E and SynthBio data-to-text datasets, we show that TempLM is more faithful than the original PLM and is more fluent than prior template systems. Notably, on an out-of-domain evaluation, TempLM reduces a finetuned BART model’s unfaithfulness rate from 83% to 0%. In a human study, we find that TempLM’s templates substantially improve upon human-written ones in BERTScore.
%R 10.18653/v1/2023.findings-acl.124
%U https://aclanthology.org/2023.findings-acl.124
%U https://doi.org/10.18653/v1/2023.findings-acl.124
%P 1970-1994

Markdown (Informal)

[TempLM: Distilling Language Models into Template-Based Generators](https://aclanthology.org/2023.findings-acl.124) (Zhang et al., Findings 2023)

• TempLM: Distilling Language Models into Template-Based Generators (Zhang et al., Findings 2023)

ACL

• Tianyi Zhang, Mina Lee, Xiang Lisa Li, Ende Shen, and Tatsunori Hashimoto. 2023. TempLM: Distilling Language Models into Template-Based Generators. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1970–1994, Toronto, Canada. Association for Computational Linguistics.