<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-utiyama-2024-continuous">
    <titleInfo>
        <title>To be Continuous, or to be Discrete, Those are Bits of Questions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yiran</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Masao</namePart>
        <namePart type="family">Utiyama</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recently, binary representation has been proposed as a novel representation that lies between continuous and discrete representations. It exhibits considerable information-preserving capability when being used to replace continuous input vectors. In this paper, we investigate the feasibility of further introducing it to the output side, aiming to allow models to output binary labels instead. To preserve the structural information on the output side along with label information, we extend the previous contrastive hashing method as structured contrastive hashing. More specifically, we upgrade CKY from label-level to bit-level, define a new similarity function with span marginal probabilities, and introduce a novel contrastive loss function with a carefully designed instance selection strategy. Our model achieves competitive performance on various structured prediction tasks, and demonstrates that binary representation can be considered a novel representation that further bridges the gap between the continuous nature of deep learning and the discrete intrinsic property of natural languages.</abstract>
    <identifier type="citekey">wang-utiyama-2024-continuous</identifier>
    <identifier type="doi">10.18653/v1/2024.acl-long.436</identifier>
    <location>
        <url>https://aclanthology.org/2024.luhme-long.436/</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>8036</start>
            <end>8049</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T To be Continuous, or to be Discrete, Those are Bits of Questions
%A Wang, Yiran
%A Utiyama, Masao
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wang-utiyama-2024-continuous
%X Recently, binary representation has been proposed as a novel representation that lies between continuous and discrete representations. It exhibits considerable information-preserving capability when being used to replace continuous input vectors. In this paper, we investigate the feasibility of further introducing it to the output side, aiming to allow models to output binary labels instead. To preserve the structural information on the output side along with label information, we extend the previous contrastive hashing method as structured contrastive hashing. More specifically, we upgrade CKY from label-level to bit-level, define a new similarity function with span marginal probabilities, and introduce a novel contrastive loss function with a carefully designed instance selection strategy. Our model achieves competitive performance on various structured prediction tasks, and demonstrates that binary representation can be considered a novel representation that further bridges the gap between the continuous nature of deep learning and the discrete intrinsic property of natural languages.
%R 10.18653/v1/2024.acl-long.436
%U https://aclanthology.org/2024.luhme-long.436/
%U https://doi.org/10.18653/v1/2024.acl-long.436
%P 8036-8049

Markdown (Informal)

[To be Continuous, or to be Discrete, Those are Bits of Questions](https://aclanthology.org/2024.luhme-long.436/) (Wang & Utiyama, ACL 2024)

• To be Continuous, or to be Discrete, Those are Bits of Questions (Wang & Utiyama, ACL 2024)

ACL

• Yiran Wang and Masao Utiyama. 2024. To be Continuous, or to be Discrete, Those are Bits of Questions. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8036–8049, Bangkok, Thailand. Association for Computational Linguistics.