<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2024-dyvo">
    <titleInfo>
        <title>DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Thong</namePart>
        <namePart type="family">Nguyen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shubham</namePart>
        <namePart type="family">Chatterjee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sean</namePart>
        <namePart type="family">MacAvaney</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Iain</namePart>
        <namePart type="family">Mackie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jeff</namePart>
        <namePart type="family">Dalton</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrew</namePart>
        <namePart type="family">Yates</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Learned Sparse Retrieval (LSR) models use vocabularies from pre-trained transformers, which often split entities into nonsensical fragments. Splitting entities diminishes retrieval accuracy and limits the model’s ability to incorporate up-to-date world knowledge not included in the training data. In this work, we enhance the LSR vocabulary with Wikipedia concepts and entities, enabling the model to resolve ambiguities more effectively and stay current with evolving knowledge. Central to our approach is a Dynamic Vocabulary (DyVo) head, which leverages existing entity embeddings and an entity retrieval component that identifies entities relevant to a query or document. We use the DyVo head to generate entity weights, which are then merged with word piece weights to create joint representations for efficient indexing and retrieval using an inverted index. In experiments across three entity-rich document ranking datasets, the resulting DyVo model substantially outperforms several state-of-the-art baselines.</abstract>
    <identifier type="citekey">nguyen-etal-2024-dyvo</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.45</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>767</start>
            <end>783</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities
%A Nguyen, Thong
%A Chatterjee, Shubham
%A MacAvaney, Sean
%A Mackie, Iain
%A Dalton, Jeff
%A Yates, Andrew
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F nguyen-etal-2024-dyvo
%X Learned Sparse Retrieval (LSR) models use vocabularies from pre-trained transformers, which often split entities into nonsensical fragments. Splitting entities diminishes retrieval accuracy and limits the model’s ability to incorporate up-to-date world knowledge not included in the training data. In this work, we enhance the LSR vocabulary with Wikipedia concepts and entities, enabling the model to resolve ambiguities more effectively and stay current with evolving knowledge. Central to our approach is a Dynamic Vocabulary (DyVo) head, which leverages existing entity embeddings and an entity retrieval component that identifies entities relevant to a query or document. We use the DyVo head to generate entity weights, which are then merged with word piece weights to create joint representations for efficient indexing and retrieval using an inverted index. In experiments across three entity-rich document ranking datasets, the resulting DyVo model substantially outperforms several state-of-the-art baselines.
%U https://aclanthology.org/2024.emnlp-main.45
%P 767-783

Markdown (Informal)

[DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities](https://aclanthology.org/2024.emnlp-main.45) (Nguyen et al., EMNLP 2024)

• DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities (Nguyen et al., EMNLP 2024)

ACL

• Thong Nguyen, Shubham Chatterjee, Sean MacAvaney, Iain Mackie, Jeff Dalton, and Andrew Yates. 2024. DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with Entities. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 767–783, Miami, Florida, USA. Association for Computational Linguistics.