@inproceedings{sun-etal-2021-enhancing,
title = "Enhancing Document Ranking with Task-adaptive Training and Segmented Token Recovery Mechanism",
author = "Sun, Xingwu and
Cui, Yanling and
Tang, Hongyin and
Zhang, Fuzheng and
Jin, Beihong and
Wang, Shi",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.289",
doi = "10.18653/v1/2021.emnlp-main.289",
pages = "3570--3579",
abstract = "In this paper, we propose a new ranking model DR-BERT, which improves the Document Retrieval (DR) task by a task-adaptive training process and a Segmented Token Recovery Mechanism (STRM). In the task-adaptive training, we first pre-train DR-BERT to be domain-adaptive and then make the two-phase fine-tuning. In the first-phase fine-tuning, the model learns query-document matching patterns regarding different query types in a pointwise way. Next, in the second-phase fine-tuning, the model learns document-level ranking features and ranks documents with regard to a given query in a listwise manner. Such pointwise plus listwise fine-tuning enables the model to minimize errors in the document ranking by incorporating ranking-specific supervisions. Meanwhile, the model derived from pointwise fine-tuning is also used to reduce noise in the training data of the listwise fine-tuning. On the other hand, we present STRM which can compute OOV word representation and contextualization more precisely in BERT-based models. As an effective strategy in DR-BERT, STRM improves the matching perfromance of OOV words between a query and a document. Notably, our DR-BERT model keeps in the top three on the MS MARCO leaderboard since May 20, 2020.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2021-enhancing">
<titleInfo>
<title>Enhancing Document Ranking with Task-adaptive Training and Segmented Token Recovery Mechanism</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xingwu</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanling</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyin</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fuzheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beihong</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose a new ranking model DR-BERT, which improves the Document Retrieval (DR) task by a task-adaptive training process and a Segmented Token Recovery Mechanism (STRM). In the task-adaptive training, we first pre-train DR-BERT to be domain-adaptive and then make the two-phase fine-tuning. In the first-phase fine-tuning, the model learns query-document matching patterns regarding different query types in a pointwise way. Next, in the second-phase fine-tuning, the model learns document-level ranking features and ranks documents with regard to a given query in a listwise manner. Such pointwise plus listwise fine-tuning enables the model to minimize errors in the document ranking by incorporating ranking-specific supervisions. Meanwhile, the model derived from pointwise fine-tuning is also used to reduce noise in the training data of the listwise fine-tuning. On the other hand, we present STRM which can compute OOV word representation and contextualization more precisely in BERT-based models. As an effective strategy in DR-BERT, STRM improves the matching perfromance of OOV words between a query and a document. Notably, our DR-BERT model keeps in the top three on the MS MARCO leaderboard since May 20, 2020.</abstract>
<identifier type="citekey">sun-etal-2021-enhancing</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.289</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.289</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3570</start>
<end>3579</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Document Ranking with Task-adaptive Training and Segmented Token Recovery Mechanism
%A Sun, Xingwu
%A Cui, Yanling
%A Tang, Hongyin
%A Zhang, Fuzheng
%A Jin, Beihong
%A Wang, Shi
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F sun-etal-2021-enhancing
%X In this paper, we propose a new ranking model DR-BERT, which improves the Document Retrieval (DR) task by a task-adaptive training process and a Segmented Token Recovery Mechanism (STRM). In the task-adaptive training, we first pre-train DR-BERT to be domain-adaptive and then make the two-phase fine-tuning. In the first-phase fine-tuning, the model learns query-document matching patterns regarding different query types in a pointwise way. Next, in the second-phase fine-tuning, the model learns document-level ranking features and ranks documents with regard to a given query in a listwise manner. Such pointwise plus listwise fine-tuning enables the model to minimize errors in the document ranking by incorporating ranking-specific supervisions. Meanwhile, the model derived from pointwise fine-tuning is also used to reduce noise in the training data of the listwise fine-tuning. On the other hand, we present STRM which can compute OOV word representation and contextualization more precisely in BERT-based models. As an effective strategy in DR-BERT, STRM improves the matching perfromance of OOV words between a query and a document. Notably, our DR-BERT model keeps in the top three on the MS MARCO leaderboard since May 20, 2020.
%R 10.18653/v1/2021.emnlp-main.289
%U https://aclanthology.org/2021.emnlp-main.289
%U https://doi.org/10.18653/v1/2021.emnlp-main.289
%P 3570-3579
Markdown (Informal)
[Enhancing Document Ranking with Task-adaptive Training and Segmented Token Recovery Mechanism](https://aclanthology.org/2021.emnlp-main.289) (Sun et al., EMNLP 2021)
ACL