<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keymanesh-etal-2022-makes">
    <titleInfo>
        <title>What Makes Data-to-Text Generation Hard for Pretrained Language Models?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Moniba</namePart>
        <namePart type="family">Keymanesh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adrian</namePart>
        <namePart type="family">Benton</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mark</namePart>
        <namePart type="family">Dredze</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Antoine</namePart>
            <namePart type="family">Bosselut</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Khyathi</namePart>
            <namePart type="family">Chandu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kaustubh</namePart>
            <namePart type="family">Dhole</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Varun</namePart>
            <namePart type="family">Gangal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Gehrmann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yacine</namePart>
            <namePart type="family">Jernite</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jekaterina</namePart>
            <namePart type="family">Novikova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Laura</namePart>
            <namePart type="family">Perez-Beltrachini</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Expressing natural language descriptions of structured facts or relations – data-to-text generation (D2T) – increases the accessibility of structured knowledge repositories. Previous work shows that pre-trained language models (PLMs) perform remarkably well on this task after fine-tuning on a significant amount of task-specific training data. On the other hand, while auto-regressive PLMs can generalize from a few task examples, their efficacy at D2T is largely unexplored. Furthermore, we have an incomplete understanding of the limits of PLMs on D2T. In this work, we conduct an empirical study of both fine-tuned and auto-regressive PLMs on the DART multi-domain D2T dataset. We consider their performance as a function of the amount of task-specific data and how the data is incorporated into the models: zero and few-shot learning, and fine-tuning of model weights. In addition, we probe the limits of PLMs by measuring performance on subsets of the evaluation data: novel predicates and abstractive test examples. To improve the performance on these subsets, we investigate two techniques: providing predicate descriptions in the context and re-ranking generated candidates by information reflected in the source. Finally, we conduct a human evaluation of model errors and show that D2T generation tasks would benefit from datasets with more careful manual curation.</abstract>
    <identifier type="citekey">keymanesh-etal-2022-makes</identifier>
    <identifier type="doi">10.18653/v1/2022.gem-1.50</identifier>
    <location>
        <url>https://aclanthology.org/2022.gem-1.50</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>539</start>
            <end>554</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T What Makes Data-to-Text Generation Hard for Pretrained Language Models?
%A Keymanesh, Moniba
%A Benton, Adrian
%A Dredze, Mark
%Y Bosselut, Antoine
%Y Chandu, Khyathi
%Y Dhole, Kaustubh
%Y Gangal, Varun
%Y Gehrmann, Sebastian
%Y Jernite, Yacine
%Y Novikova, Jekaterina
%Y Perez-Beltrachini, Laura
%S Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F keymanesh-etal-2022-makes
%X Expressing natural language descriptions of structured facts or relations – data-to-text generation (D2T) – increases the accessibility of structured knowledge repositories. Previous work shows that pre-trained language models (PLMs) perform remarkably well on this task after fine-tuning on a significant amount of task-specific training data. On the other hand, while auto-regressive PLMs can generalize from a few task examples, their efficacy at D2T is largely unexplored. Furthermore, we have an incomplete understanding of the limits of PLMs on D2T. In this work, we conduct an empirical study of both fine-tuned and auto-regressive PLMs on the DART multi-domain D2T dataset. We consider their performance as a function of the amount of task-specific data and how the data is incorporated into the models: zero and few-shot learning, and fine-tuning of model weights. In addition, we probe the limits of PLMs by measuring performance on subsets of the evaluation data: novel predicates and abstractive test examples. To improve the performance on these subsets, we investigate two techniques: providing predicate descriptions in the context and re-ranking generated candidates by information reflected in the source. Finally, we conduct a human evaluation of model errors and show that D2T generation tasks would benefit from datasets with more careful manual curation.
%R 10.18653/v1/2022.gem-1.50
%U https://aclanthology.org/2022.gem-1.50
%U https://doi.org/10.18653/v1/2022.gem-1.50
%P 539-554

Markdown (Informal)

[What Makes Data-to-Text Generation Hard for Pretrained Language Models?](https://aclanthology.org/2022.gem-1.50) (Keymanesh et al., GEM 2022)

• What Makes Data-to-Text Generation Hard for Pretrained Language Models? (Keymanesh et al., GEM 2022)

ACL

• Moniba Keymanesh, Adrian Benton, and Mark Dredze. 2022. What Makes Data-to-Text Generation Hard for Pretrained Language Models?. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 539–554, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.