<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiong-etal-2023-adapting">
    <titleInfo>
        <title>Adapting Pretrained Text-to-Text Models for Long Text Sequences</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wenhan</namePart>
        <namePart type="family">Xiong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anchit</namePart>
        <namePart type="family">Gupta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shubham</namePart>
        <namePart type="family">Toshniwal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yashar</namePart>
        <namePart type="family">Mehdad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Scott</namePart>
        <namePart type="family">Yih</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present an empirical study of adapting an existing pretrained text-to-text model for long-sequence inputs. Through a comprehensive study along three axes of the pretraining pipeline – model architecture, optimization objective, and pretraining corpus, we propose an effective recipe to build long-context models from existing short-context models. Specifically, we replace the full attention in transformers with pooling-augmented blockwise attention, and pretrain the model with a masked-span prediction task with spans of varying lengths. In terms of the pretraining corpus, we find that using randomly concatenated short-documents from a large open-domain corpus results in better performance than using existing long document corpora, which are typically limited in their domain coverage. With these findings, we build a long-context model that achieves competitive performance on long-text QA tasks and establishes the new state of the art on five long-text summarization datasets, often outperforming previous methods with larger model sizes.</abstract>
    <identifier type="citekey">xiong-etal-2023-adapting</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.370</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.370</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>5566</start>
            <end>5578</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Adapting Pretrained Text-to-Text Models for Long Text Sequences
%A Xiong, Wenhan
%A Gupta, Anchit
%A Toshniwal, Shubham
%A Mehdad, Yashar
%A Yih, Scott
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F xiong-etal-2023-adapting
%X We present an empirical study of adapting an existing pretrained text-to-text model for long-sequence inputs. Through a comprehensive study along three axes of the pretraining pipeline – model architecture, optimization objective, and pretraining corpus, we propose an effective recipe to build long-context models from existing short-context models. Specifically, we replace the full attention in transformers with pooling-augmented blockwise attention, and pretrain the model with a masked-span prediction task with spans of varying lengths. In terms of the pretraining corpus, we find that using randomly concatenated short-documents from a large open-domain corpus results in better performance than using existing long document corpora, which are typically limited in their domain coverage. With these findings, we build a long-context model that achieves competitive performance on long-text QA tasks and establishes the new state of the art on five long-text summarization datasets, often outperforming previous methods with larger model sizes.
%R 10.18653/v1/2023.findings-emnlp.370
%U https://aclanthology.org/2023.findings-emnlp.370
%U https://doi.org/10.18653/v1/2023.findings-emnlp.370
%P 5566-5578

Markdown (Informal)

[Adapting Pretrained Text-to-Text Models for Long Text Sequences](https://aclanthology.org/2023.findings-emnlp.370) (Xiong et al., Findings 2023)

• Adapting Pretrained Text-to-Text Models for Long Text Sequences (Xiong et al., Findings 2023)

ACL

• Wenhan Xiong, Anchit Gupta, Shubham Toshniwal, Yashar Mehdad, and Scott Yih. 2023. Adapting Pretrained Text-to-Text Models for Long Text Sequences. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5566–5578, Singapore. Association for Computational Linguistics.