Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rank

This paper describes the approach of the THUIR team at the WSDM Cup 2023 Pre-training for Web Search task. This task requires the participant to rank the relevant documents for each query. We propose a new data pre-processing method and conduct pre-training and fine-tuning with the processed data. M...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Li, Haitao, Chen, Jia, Su, Weihang, Ai, Qingyao, Liu, Yiqun
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Information Retrieval
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page
container_issue
container_start_page
container_title
container_volume
creator	Li, Haitao Chen, Jia Su, Weihang Ai, Qingyao Liu, Yiqun
description	This paper describes the approach of the THUIR team at the WSDM Cup 2023 Pre-training for Web Search task. This task requires the participant to rank the relevant documents for each query. We propose a new data pre-processing method and conduct pre-training and fine-tuning with the processed data. Moreover, we extract statistical, axiomatic, and semantic features to enhance the ranking performance. After the feature extraction, diverse learning-to-rank models are employed to merge those features. The experimental results show the superiority of our proposal. We finally achieve second place in this competition.
doi_str_mv	10.48550/arxiv.2303.04710
format	Article
fullrecord	<record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2303_04710</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2303_04710</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-195d49bfadbb78d267dd37561443093fb3a482ac9b381b060ef00f0d4bb194983</originalsourceid><addsrcrecordid>eNotj71OwzAURr0woMIDMOEHIOE6dmKbDSoKSJGo2iDG6Dq2IYI66Db8vX3bwPTpDN-RDmNnAnJlyhIukX76r7yQIHNQWsAxe2qGbyS_5TdhHAPx5-D4OiB1r3wZKA60wdSFK76kkI2EferTywVf9GmPnwfgmDyv948JxoGvML2dsKOI79tw-r8z1ixum_l9Vj_ePcyv6wwrDZmwpVfWRfTOaeOLSnsvdVkJpSRYGZ1EZQrsrJNGOKggRIAIXjknrLJGztj5n3bqaj-o3yD9toe-duqTO01HSis</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rank</title><source>arXiv.org</source><creator>Li, Haitao ; Chen, Jia ; Su, Weihang ; Ai, Qingyao ; Liu, Yiqun</creator><creatorcontrib>Li, Haitao ; Chen, Jia ; Su, Weihang ; Ai, Qingyao ; Liu, Yiqun</creatorcontrib><description>This paper describes the approach of the THUIR team at the WSDM Cup 2023 Pre-training for Web Search task. This task requires the participant to rank the relevant documents for each query. We propose a new data pre-processing method and conduct pre-training and fine-tuning with the processed data. Moreover, we extract statistical, axiomatic, and semantic features to enhance the ranking performance. After the feature extraction, diverse learning-to-rank models are employed to merge those features. The experimental results show the superiority of our proposal. We finally achieve second place in this competition.</description><identifier>DOI: 10.48550/arxiv.2303.04710</identifier><language>eng</language><subject>Computer Science - Information Retrieval</subject><creationdate>2023-02</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,886</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2303.04710$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2303.04710$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Li, Haitao</creatorcontrib><creatorcontrib>Chen, Jia</creatorcontrib><creatorcontrib>Su, Weihang</creatorcontrib><creatorcontrib>Ai, Qingyao</creatorcontrib><creatorcontrib>Liu, Yiqun</creatorcontrib><title>Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rank</title><description>This paper describes the approach of the THUIR team at the WSDM Cup 2023 Pre-training for Web Search task. This task requires the participant to rank the relevant documents for each query. We propose a new data pre-processing method and conduct pre-training and fine-tuning with the processed data. Moreover, we extract statistical, axiomatic, and semantic features to enhance the ranking performance. After the feature extraction, diverse learning-to-rank models are employed to merge those features. The experimental results show the superiority of our proposal. We finally achieve second place in this competition.</description><subject>Computer Science - Information Retrieval</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj71OwzAURr0woMIDMOEHIOE6dmKbDSoKSJGo2iDG6Dq2IYI66Db8vX3bwPTpDN-RDmNnAnJlyhIukX76r7yQIHNQWsAxe2qGbyS_5TdhHAPx5-D4OiB1r3wZKA60wdSFK76kkI2EferTywVf9GmPnwfgmDyv948JxoGvML2dsKOI79tw-r8z1ixum_l9Vj_ePcyv6wwrDZmwpVfWRfTOaeOLSnsvdVkJpSRYGZ1EZQrsrJNGOKggRIAIXjknrLJGztj5n3bqaj-o3yD9toe-duqTO01HSis</recordid><startdate>20230228</startdate><enddate>20230228</enddate><creator>Li, Haitao</creator><creator>Chen, Jia</creator><creator>Su, Weihang</creator><creator>Ai, Qingyao</creator><creator>Liu, Yiqun</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230228</creationdate><title>Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rank</title><author>Li, Haitao ; Chen, Jia ; Su, Weihang ; Ai, Qingyao ; Liu, Yiqun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-195d49bfadbb78d267dd37561443093fb3a482ac9b381b060ef00f0d4bb194983</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Information Retrieval</topic><toplevel>online_resources</toplevel><creatorcontrib>Li, Haitao</creatorcontrib><creatorcontrib>Chen, Jia</creatorcontrib><creatorcontrib>Su, Weihang</creatorcontrib><creatorcontrib>Ai, Qingyao</creatorcontrib><creatorcontrib>Liu, Yiqun</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Li, Haitao</au><au>Chen, Jia</au><au>Su, Weihang</au><au>Ai, Qingyao</au><au>Liu, Yiqun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rank</atitle><date>2023-02-28</date><risdate>2023</risdate><abstract>This paper describes the approach of the THUIR team at the WSDM Cup 2023 Pre-training for Web Search task. This task requires the participant to rank the relevant documents for each query. We propose a new data pre-processing method and conduct pre-training and fine-tuning with the processed data. Moreover, we extract statistical, axiomatic, and semantic features to enhance the ranking performance. After the feature extraction, diverse learning-to-rank models are employed to merge those features. The experimental results show the superiority of our proposal. We finally achieve second place in this competition.</abstract><doi>10.48550/arxiv.2303.04710</doi><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	DOI: 10.48550/arxiv.2303.04710
ispartof
issn
language	eng
recordid	cdi_arxiv_primary_2303_04710
source	arXiv.org
subjects	Computer Science - Information Retrieval
title	Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rank
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-11T19%3A19%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Towards%20Better%20Web%20Search%20Performance:%20Pre-training,%20Fine-tuning%20and%20Learning%20to%20Rank&rft.au=Li,%20Haitao&rft.date=2023-02-28&rft_id=info:doi/10.48550/arxiv.2303.04710&rft_dat=%3Carxiv_GOX%3E2303_04710%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true