Existing news recommendation methods usually learn news representations solely based on news titles. To sufficiently utilize other fields of news information such as category and entities, some methods treat each field as an additional feature and combine different feature vectors with attentive pooling. With the adoption of large pre-trained models like BERT in news recommendation, the above way to incorporate multi-field information may encounter challenges: the shallow feature encoding to compress the category and entity information is not compatible with the deep BERT encoding. In this paper, we propose a multi-task method to incorporate the multi-field information into BERT, which improves its news encoding capability. Besides, we modify the gradients of auxiliary tasks based on their gradient conflicts with the main task, which further boosts the model performance. Extensive experiments on the MIND news recommendation benchmark show the effectiveness of our approach.
Qiwei Bi, Jian Li, Lifeng Shang, Xin Jiang, Qun Liu, and Hanfang Yang. 2022.MTRec: Multi-Task Learning over BERT for News Recommendation. InFindings of the Association for Computational Linguistics: ACL 2022, pages 2663–2669, Dublin, Ireland. Association for Computational Linguistics.
@inproceedings{bi-etal-2022-mtrec, title = "{MTR}ec: Multi-Task Learning over {BERT} for News Recommendation", author = "Bi, Qiwei and Li, Jian and Shang, Lifeng and Jiang, Xin and Liu, Qun and Yang, Hanfang", editor = "Muresan, Smaranda and Nakov, Preslav and Villavicencio, Aline", booktitle = "Findings of the Association for Computational Linguistics: ACL 2022", month = may, year = "2022", address = "Dublin, Ireland", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2022.findings-acl.209/", doi = "10.18653/v1/2022.findings-acl.209", pages = "2663--2669", abstract = "Existing news recommendation methods usually learn news representations solely based on news titles. To sufficiently utilize other fields of news information such as category and entities, some methods treat each field as an additional feature and combine different feature vectors with attentive pooling. With the adoption of large pre-trained models like BERT in news recommendation, the above way to incorporate multi-field information may encounter challenges: the shallow feature encoding to compress the category and entity information is not compatible with the deep BERT encoding. In this paper, we propose a multi-task method to incorporate the multi-field information into BERT, which improves its news encoding capability. Besides, we modify the gradients of auxiliary tasks based on their gradient conflicts with the main task, which further boosts the model performance. Extensive experiments on the MIND news recommendation benchmark show the effectiveness of our approach."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="bi-etal-2022-mtrec"> <titleInfo> <title>MTRec: Multi-Task Learning over BERT for News Recommendation</title> </titleInfo> <name type="personal"> <namePart type="given">Qiwei</namePart> <namePart type="family">Bi</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Jian</namePart> <namePart type="family">Li</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Lifeng</namePart> <namePart type="family">Shang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Xin</namePart> <namePart type="family">Jiang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Qun</namePart> <namePart type="family">Liu</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Hanfang</namePart> <namePart type="family">Yang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2022-05</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Findings of the Association for Computational Linguistics: ACL 2022</title> </titleInfo> <name type="personal"> <namePart type="given">Smaranda</namePart> <namePart type="family">Muresan</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Preslav</namePart> <namePart type="family">Nakov</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Aline</namePart> <namePart type="family">Villavicencio</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Dublin, Ireland</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>Existing news recommendation methods usually learn news representations solely based on news titles. To sufficiently utilize other fields of news information such as category and entities, some methods treat each field as an additional feature and combine different feature vectors with attentive pooling. With the adoption of large pre-trained models like BERT in news recommendation, the above way to incorporate multi-field information may encounter challenges: the shallow feature encoding to compress the category and entity information is not compatible with the deep BERT encoding. In this paper, we propose a multi-task method to incorporate the multi-field information into BERT, which improves its news encoding capability. Besides, we modify the gradients of auxiliary tasks based on their gradient conflicts with the main task, which further boosts the model performance. Extensive experiments on the MIND news recommendation benchmark show the effectiveness of our approach.</abstract> <identifier type="citekey">bi-etal-2022-mtrec</identifier> <identifier type="doi">10.18653/v1/2022.findings-acl.209</identifier> <location> <url>https://aclanthology.org/2022.findings-acl.209/</url> </location> <part> <date>2022-05</date> <extent unit="page"> <start>2663</start> <end>2669</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T MTRec: Multi-Task Learning over BERT for News Recommendation%A Bi, Qiwei%A Li, Jian%A Shang, Lifeng%A Jiang, Xin%A Liu, Qun%A Yang, Hanfang%Y Muresan, Smaranda%Y Nakov, Preslav%Y Villavicencio, Aline%S Findings of the Association for Computational Linguistics: ACL 2022%D 2022%8 May%I Association for Computational Linguistics%C Dublin, Ireland%F bi-etal-2022-mtrec%X Existing news recommendation methods usually learn news representations solely based on news titles. To sufficiently utilize other fields of news information such as category and entities, some methods treat each field as an additional feature and combine different feature vectors with attentive pooling. With the adoption of large pre-trained models like BERT in news recommendation, the above way to incorporate multi-field information may encounter challenges: the shallow feature encoding to compress the category and entity information is not compatible with the deep BERT encoding. In this paper, we propose a multi-task method to incorporate the multi-field information into BERT, which improves its news encoding capability. Besides, we modify the gradients of auxiliary tasks based on their gradient conflicts with the main task, which further boosts the model performance. Extensive experiments on the MIND news recommendation benchmark show the effectiveness of our approach.%R 10.18653/v1/2022.findings-acl.209%U https://aclanthology.org/2022.findings-acl.209/%U https://doi.org/10.18653/v1/2022.findings-acl.209%P 2663-2669
Qiwei Bi, Jian Li, Lifeng Shang, Xin Jiang, Qun Liu, and Hanfang Yang. 2022.MTRec: Multi-Task Learning over BERT for News Recommendation. InFindings of the Association for Computational Linguistics: ACL 2022, pages 2663–2669, Dublin, Ireland. Association for Computational Linguistics.