<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chiu-shinzato-2022-cross">
    <titleInfo>
        <title>Cross-Encoder Data Annotation for Bi-Encoder Based Product Matching</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Justin</namePart>
        <namePart type="family">Chiu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Keiji</namePart>
        <namePart type="family">Shinzato</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yunyao</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Angeliki</namePart>
            <namePart type="family">Lazaridou</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, UAE</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Matching a seller listed item to an appropriate product is an important step for an e-commerce platform. With the recent advancement in deep learning, there are different encoder based approaches being proposed as solution. When textual data for two products are available, cross-encoder approaches encode them jointly while bi-encoder approaches encode them separately. Since cross-encoders are computationally heavy, approaches based on bi-encoders are a common practice for this challenge. In this paper, we propose cross-encoder data annotation; a technique to annotate or refine human annotated training data for bi-encoder models using a cross-encoder model. This technique enables us to build a robust model without annotation on newly collected training data or further improve model performance on annotated training data. We evaluate the cross-encoder data annotation on the product matching task using a real-world e-commerce dataset containing 104 million products. Experimental results show that the cross-encoder data annotation improves 4% absolute accuracy when no annotation for training data is available, and 2% absolute accuracy when annotation for training data is available.</abstract>
    <identifier type="citekey">chiu-shinzato-2022-cross</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-industry.16</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-industry.16</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>161</start>
            <end>168</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cross-Encoder Data Annotation for Bi-Encoder Based Product Matching
%A Chiu, Justin
%A Shinzato, Keiji
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F chiu-shinzato-2022-cross
%X Matching a seller listed item to an appropriate product is an important step for an e-commerce platform. With the recent advancement in deep learning, there are different encoder based approaches being proposed as solution. When textual data for two products are available, cross-encoder approaches encode them jointly while bi-encoder approaches encode them separately. Since cross-encoders are computationally heavy, approaches based on bi-encoders are a common practice for this challenge. In this paper, we propose cross-encoder data annotation; a technique to annotate or refine human annotated training data for bi-encoder models using a cross-encoder model. This technique enables us to build a robust model without annotation on newly collected training data or further improve model performance on annotated training data. We evaluate the cross-encoder data annotation on the product matching task using a real-world e-commerce dataset containing 104 million products. Experimental results show that the cross-encoder data annotation improves 4% absolute accuracy when no annotation for training data is available, and 2% absolute accuracy when annotation for training data is available.
%R 10.18653/v1/2022.emnlp-industry.16
%U https://aclanthology.org/2022.emnlp-industry.16
%U https://doi.org/10.18653/v1/2022.emnlp-industry.16
%P 161-168

Markdown (Informal)

[Cross-Encoder Data Annotation for Bi-Encoder Based Product Matching](https://aclanthology.org/2022.emnlp-industry.16) (Chiu & Shinzato, EMNLP 2022)

• Cross-Encoder Data Annotation for Bi-Encoder Based Product Matching (Chiu & Shinzato, EMNLP 2022)

ACL

• Justin Chiu and Keiji Shinzato. 2022. Cross-Encoder Data Annotation for Bi-Encoder Based Product Matching. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 161–168, Abu Dhabi, UAE. Association for Computational Linguistics.