<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2023-trams">
    <titleInfo>
        <title>TRAMS: Training-free Memory Selection for Long-range Language Modeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haofei</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cunxiang</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yue</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Bi</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>The Transformer architecture is crucial for numerous AI models, but it still faces challenges in long-range language modeling. Though several specific transformer architectures have been designed to tackle issues of long-range dependencies, existing methods like Transformer-XL are plagued by a high percentage of ineffective memories. In this study, we present a plug-and-play strategy, known as TRAining-free Memory Selection (TRAMS), that selects tokens participating in attention calculation based on one simple metric. This strategy allows us to keep tokens that are likely to have a high attention score with the current queries and ignore the other ones. We have tested our approach on the word-level benchmark (WikiText-103) and the character-level benchmark (enwik8), and the results indicate an improvement without having additional training or adding additional parameters.</abstract>
    <identifier type="citekey">yu-etal-2023-trams</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.331</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.331/</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>4966</start>
            <end>4972</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TRAMS: Training-free Memory Selection for Long-range Language Modeling
%A Yu, Haofei
%A Wang, Cunxiang
%A Zhang, Yue
%A Bi, Wei
%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 yu-etal-2023-trams
%X The Transformer architecture is crucial for numerous AI models, but it still faces challenges in long-range language modeling. Though several specific transformer architectures have been designed to tackle issues of long-range dependencies, existing methods like Transformer-XL are plagued by a high percentage of ineffective memories. In this study, we present a plug-and-play strategy, known as TRAining-free Memory Selection (TRAMS), that selects tokens participating in attention calculation based on one simple metric. This strategy allows us to keep tokens that are likely to have a high attention score with the current queries and ignore the other ones. We have tested our approach on the word-level benchmark (WikiText-103) and the character-level benchmark (enwik8), and the results indicate an improvement without having additional training or adding additional parameters.
%R 10.18653/v1/2023.findings-emnlp.331
%U https://aclanthology.org/2023.findings-emnlp.331/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.331
%P 4966-4972

Markdown (Informal)

[TRAMS: Training-free Memory Selection for Long-range Language Modeling](https://aclanthology.org/2023.findings-emnlp.331/) (Yu et al., Findings 2023)

• TRAMS: Training-free Memory Selection for Long-range Language Modeling (Yu et al., Findings 2023)

ACL

• Haofei Yu, Cunxiang Wang, Yue Zhang, and Wei Bi. 2023. TRAMS: Training-free Memory Selection for Long-range Language Modeling. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4966–4972, Singapore. Association for Computational Linguistics.