@inproceedings{chen-etal-2022-effective,
title = "An Effective Post-training Embedding Binarization Approach for Fast Online Top-K Passage Matching",
author = "Chen, Yankai and
Zhang, Yifei and
Guo, Huifeng and
Tang, Ruiming and
King, Irwin",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-short.14",
pages = "102--108",
abstract = "With the rapid development of Natural Language Understanding for information retrieval, fine-tuned deep language models, e.g., BERT-based, perform remarkably effective in passage searching tasks. To lower the architecture complexity, the recent state-of-the-art model ColBERT employs Contextualized Late Interaction paradigm to independently learn fine-grained query-passage representations. Apart from the architecture simplification, embedding binarization, as another promising branch in model compression, further specializes in the reduction of memory and computation overheads. In this concise paper, we propose an effective post-training embedding binarization approach over ColBERT, achieving both architecture-level and embedding-level optimization for online inference. The empirical results demonstrate the efficaciousness of our proposed approach, empowering it to perform online query-passage matching acceleration.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-effective">
<titleInfo>
<title>An Effective Post-training Embedding Binarization Approach for Fast Online Top-K Passage Matching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yankai</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huifeng</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiming</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irwin</namePart>
<namePart type="family">King</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the rapid development of Natural Language Understanding for information retrieval, fine-tuned deep language models, e.g., BERT-based, perform remarkably effective in passage searching tasks. To lower the architecture complexity, the recent state-of-the-art model ColBERT employs Contextualized Late Interaction paradigm to independently learn fine-grained query-passage representations. Apart from the architecture simplification, embedding binarization, as another promising branch in model compression, further specializes in the reduction of memory and computation overheads. In this concise paper, we propose an effective post-training embedding binarization approach over ColBERT, achieving both architecture-level and embedding-level optimization for online inference. The empirical results demonstrate the efficaciousness of our proposed approach, empowering it to perform online query-passage matching acceleration.</abstract>
<identifier type="citekey">chen-etal-2022-effective</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-short.14</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>102</start>
<end>108</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Effective Post-training Embedding Binarization Approach for Fast Online Top-K Passage Matching
%A Chen, Yankai
%A Zhang, Yifei
%A Guo, Huifeng
%A Tang, Ruiming
%A King, Irwin
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F chen-etal-2022-effective
%X With the rapid development of Natural Language Understanding for information retrieval, fine-tuned deep language models, e.g., BERT-based, perform remarkably effective in passage searching tasks. To lower the architecture complexity, the recent state-of-the-art model ColBERT employs Contextualized Late Interaction paradigm to independently learn fine-grained query-passage representations. Apart from the architecture simplification, embedding binarization, as another promising branch in model compression, further specializes in the reduction of memory and computation overheads. In this concise paper, we propose an effective post-training embedding binarization approach over ColBERT, achieving both architecture-level and embedding-level optimization for online inference. The empirical results demonstrate the efficaciousness of our proposed approach, empowering it to perform online query-passage matching acceleration.
%U https://aclanthology.org/2022.aacl-short.14
%P 102-108
Markdown (Informal)
[An Effective Post-training Embedding Binarization Approach for Fast Online Top-K Passage Matching](https://aclanthology.org/2022.aacl-short.14) (Chen et al., AACL-IJCNLP 2022)
ACL