<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-text">
    <titleInfo>
        <title>Text Representation Distillation via Information Bottleneck Principle</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yanzhao</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dingkun</namePart>
        <namePart type="family">Long</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zehan</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pengjun</namePart>
        <namePart type="family">Xie</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>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</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>Pre-trained language models (PLMs) have recently shown great success in text representation field. However, the high computational cost and high-dimensional representation of PLMs pose significant challenges for practical applications. To make models more accessible, an effective method is to distill large models into smaller representation models. In order to relieve the issue of performance degradation after distillation, we propose a novel Knowledge Distillation method called IBKD. This approach is motivated by the Information Bottleneck principle and aims to maximize the mutual information between the final representation of the teacher and student model, while simultaneously reducing the mutual information between the student model‘s representation and the input data. This enables the student model to preserve important learned information while avoiding unnecessary information, thus reducing the risk of over-fitting. Empirical studies on two main downstream applications of text representation (Semantic Textual Similarity and Dense Retrieval tasks) demonstrate the effectiveness of our proposed approach.</abstract>
    <identifier type="citekey">zhang-etal-2023-text</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.888</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.888/</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>14372</start>
            <end>14383</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Text Representation Distillation via Information Bottleneck Principle
%A Zhang, Yanzhao
%A Long, Dingkun
%A Li, Zehan
%A Xie, Pengjun
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhang-etal-2023-text
%X Pre-trained language models (PLMs) have recently shown great success in text representation field. However, the high computational cost and high-dimensional representation of PLMs pose significant challenges for practical applications. To make models more accessible, an effective method is to distill large models into smaller representation models. In order to relieve the issue of performance degradation after distillation, we propose a novel Knowledge Distillation method called IBKD. This approach is motivated by the Information Bottleneck principle and aims to maximize the mutual information between the final representation of the teacher and student model, while simultaneously reducing the mutual information between the student model‘s representation and the input data. This enables the student model to preserve important learned information while avoiding unnecessary information, thus reducing the risk of over-fitting. Empirical studies on two main downstream applications of text representation (Semantic Textual Similarity and Dense Retrieval tasks) demonstrate the effectiveness of our proposed approach.
%R 10.18653/v1/2023.emnlp-main.888
%U https://aclanthology.org/2023.emnlp-main.888/
%U https://doi.org/10.18653/v1/2023.emnlp-main.888
%P 14372-14383

Markdown (Informal)

[Text Representation Distillation via Information Bottleneck Principle](https://aclanthology.org/2023.emnlp-main.888/) (Zhang et al., EMNLP 2023)

• Text Representation Distillation via Information Bottleneck Principle (Zhang et al., EMNLP 2023)

ACL

• Yanzhao Zhang, Dingkun Long, Zehan Li, and Pengjun Xie. 2023. Text Representation Distillation via Information Bottleneck Principle. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 14372–14383, Singapore. Association for Computational Linguistics.