The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Compte tenu du nombre rapidement croissant d’articles universitaires, rechercher et citer des références appropriées est devenu une tâche non triviale lors de la composition d’un manuscrit. Recommander une poignée d’articles candidats à une ébauche de travail pourrait alléger le fardeau des auteurs. Les approches conventionnelles de recommandation de citations envisagent généralement de recommander une citation de vérité terrain à partir d'un manuscrit d'entrée pour un contexte de requête. Cependant, il est courant qu’un contexte donné soit soutenu par deux ou plusieurs paires de co-citations. Nous proposons ici une nouvelle modélisation d'articles scientifiques pour les recommandations de citations, à savoir le modèle BERT multi-positif pour la recommandation de citations (MP-BERT4REC), conforme à une série d'objectifs triplet multi-positifs pour recommander plusieurs citations positives pour un contexte de requête. L'approche proposée présente les avantages suivants : Premièrement, les objectifs multi-positifs proposés sont efficaces pour recommander plusieurs candidats positifs. Deuxièmement, nous adoptons des distributions de bruit sur la base des fréquences de co-citation historiques ; ainsi, MP-BERT4REC est non seulement efficace pour recommander des paires de co-citation à haute fréquence, mais il améliore également considérablement les performances de récupération des paires de co-citation à basse fréquence. Troisièmement, la stratégie d'échantillonnage de contexte dynamique proposée capture les intentions de citation macroscopiques d'un manuscrit et permet aux intégrations de citations de dépendre du contenu, ce qui permet à l'algorithme d'améliorer encore les performances. Des expériences de recommandation positive unique et multiple ont confirmé que MP-BERT4REC apporte des améliorations significatives par rapport aux méthodes actuelles. Il récupère également efficacement la liste complète des co-citations et des paires historiquement basses fréquences, mieux que les travaux antérieurs.
Yang ZHANG
China Construction Bank
Qiang MA
Kyoto University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Yang ZHANG, Qiang MA, "MP-BERT4REC: Recommending Multiple Positive Citations for Academic Manuscripts via Content-Dependent BERT and Multi-Positive Triplet" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 11, pp. 1957-1968, November 2022, doi: 10.1587/transinf.2022EDP7034.
Abstract: Considering the rapidly increasing number of academic papers, searching for and citing appropriate references has become a nontrivial task during manuscript composition. Recommending a handful of candidate papers to a working draft could ease the burden of the authors. Conventional approaches to citation recommendation generally consider recommending one ground-truth citation from an input manuscript for a query context. However, it is common for a given context to be supported by two or more co-citation pairs. Here, we propose a novel scientific paper modelling for citation recommendations, namely Multi-Positive BERT Model for Citation Recommendation (MP-BERT4REC), complied with a series of Multi-Positive Triplet objectives to recommend multiple positive citations for a query context. The proposed approach has the following advantages: First, the proposed multi-positive objectives are effective in recommending multiple positive candidates. Second, we adopt noise distributions on the basis of historical co-citation frequencies; thus, MP-BERT4REC is not only effective in recommending high-frequency co-citation pairs, but it also significantly improves the performance of retrieving low-frequency ones. Third, the proposed dynamic context sampling strategy captures macroscopic citing intents from a manuscript and empowers the citation embeddings to be content-dependent, which allows the algorithm to further improve performance. Single and multiple positive recommendation experiments confirmed that MP-BERT4REC delivers significant improvements over current methods. It also effectively retrieves the full list of co-citations and historically low-frequency pairs better than prior works.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7034/_p
Copier
@ARTICLE{e105-d_11_1957,
author={Yang ZHANG, Qiang MA, },
journal={IEICE TRANSACTIONS on Information},
title={MP-BERT4REC: Recommending Multiple Positive Citations for Academic Manuscripts via Content-Dependent BERT and Multi-Positive Triplet},
year={2022},
volume={E105-D},
number={11},
pages={1957-1968},
abstract={Considering the rapidly increasing number of academic papers, searching for and citing appropriate references has become a nontrivial task during manuscript composition. Recommending a handful of candidate papers to a working draft could ease the burden of the authors. Conventional approaches to citation recommendation generally consider recommending one ground-truth citation from an input manuscript for a query context. However, it is common for a given context to be supported by two or more co-citation pairs. Here, we propose a novel scientific paper modelling for citation recommendations, namely Multi-Positive BERT Model for Citation Recommendation (MP-BERT4REC), complied with a series of Multi-Positive Triplet objectives to recommend multiple positive citations for a query context. The proposed approach has the following advantages: First, the proposed multi-positive objectives are effective in recommending multiple positive candidates. Second, we adopt noise distributions on the basis of historical co-citation frequencies; thus, MP-BERT4REC is not only effective in recommending high-frequency co-citation pairs, but it also significantly improves the performance of retrieving low-frequency ones. Third, the proposed dynamic context sampling strategy captures macroscopic citing intents from a manuscript and empowers the citation embeddings to be content-dependent, which allows the algorithm to further improve performance. Single and multiple positive recommendation experiments confirmed that MP-BERT4REC delivers significant improvements over current methods. It also effectively retrieves the full list of co-citations and historically low-frequency pairs better than prior works.},
keywords={},
doi={10.1587/transinf.2022EDP7034},
ISSN={1745-1361},
month={November},}
Copier
TY - JOUR
TI - MP-BERT4REC: Recommending Multiple Positive Citations for Academic Manuscripts via Content-Dependent BERT and Multi-Positive Triplet
T2 - IEICE TRANSACTIONS on Information
SP - 1957
EP - 1968
AU - Yang ZHANG
AU - Qiang MA
PY - 2022
DO - 10.1587/transinf.2022EDP7034
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2022
AB - Considering the rapidly increasing number of academic papers, searching for and citing appropriate references has become a nontrivial task during manuscript composition. Recommending a handful of candidate papers to a working draft could ease the burden of the authors. Conventional approaches to citation recommendation generally consider recommending one ground-truth citation from an input manuscript for a query context. However, it is common for a given context to be supported by two or more co-citation pairs. Here, we propose a novel scientific paper modelling for citation recommendations, namely Multi-Positive BERT Model for Citation Recommendation (MP-BERT4REC), complied with a series of Multi-Positive Triplet objectives to recommend multiple positive citations for a query context. The proposed approach has the following advantages: First, the proposed multi-positive objectives are effective in recommending multiple positive candidates. Second, we adopt noise distributions on the basis of historical co-citation frequencies; thus, MP-BERT4REC is not only effective in recommending high-frequency co-citation pairs, but it also significantly improves the performance of retrieving low-frequency ones. Third, the proposed dynamic context sampling strategy captures macroscopic citing intents from a manuscript and empowers the citation embeddings to be content-dependent, which allows the algorithm to further improve performance. Single and multiple positive recommendation experiments confirmed that MP-BERT4REC delivers significant improvements over current methods. It also effectively retrieves the full list of co-citations and historically low-frequency pairs better than prior works.
ER -