{"title":"Leveraging multiple control codes for aspect-controllable related paper recommendation","authors":"","doi":"10.1016/j.ipm.2024.103879","DOIUrl":null,"url":null,"abstract":"<div><p>Aspect-Controllable Related Papers Recommendation (ACRPR) aims to satisfy users’ fine-grained needs for specific aspects when finding related papers. Existing approaches rely on the segmentation of texts or aspects to independently learn multi-aspect representations of papers. However, different aspects of a paper are guided by its overall theme and interconnected with intrinsic relevance. In light of this, we propose a simple yet effective ACRPR framework called mCTRL, which leverages multiple control codes in Transformer to simultaneously learn multiple aspect-specific paper representations. Specifically, mCTRL incorporates a <span><math><mrow><mo>[</mo><mi>CLS</mi><mo>]</mo></mrow></math></span> control code to capture the overall theme and multiple <span><math><mrow><mo>[</mo><mi>ASP</mi><mo>]</mo></mrow></math></span> control codes to exploit fine-grained aspect information. Additionally, we introduce a hierarchical loss function to balance the overall theme and various aspects of a paper, enabling their mutual enhancement and alignment. Extensive comparative experiments on real-world datasets demonstrate the superiority of our proposed method over previous state-of-the-art approaches. Evaluations are conducted on 5 backbone models and 5 dimensions, which confirm the generalization ability of mCTRL. Moreover, ablation studies and further analyses prove the effectiveness and efficiency of mCTRL and the specialization across aspects of generated embeddings.</p></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":null,"pages":null},"PeriodicalIF":7.4000,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0306457324002383/pdfft?md5=0ecc8829bb073ea6a26c7be03598c33b&pid=1-s2.0-S0306457324002383-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information Processing & Management","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0306457324002383","RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Aspect-Controllable Related Papers Recommendation (ACRPR) aims to satisfy users’ fine-grained needs for specific aspects when finding related papers. Existing approaches rely on the segmentation of texts or aspects to independently learn multi-aspect representations of papers. However, different aspects of a paper are guided by its overall theme and interconnected with intrinsic relevance. In light of this, we propose a simple yet effective ACRPR framework called mCTRL, which leverages multiple control codes in Transformer to simultaneously learn multiple aspect-specific paper representations. Specifically, mCTRL incorporates a control code to capture the overall theme and multiple control codes to exploit fine-grained aspect information. Additionally, we introduce a hierarchical loss function to balance the overall theme and various aspects of a paper, enabling their mutual enhancement and alignment. Extensive comparative experiments on real-world datasets demonstrate the superiority of our proposed method over previous state-of-the-art approaches. Evaluations are conducted on 5 backbone models and 5 dimensions, which confirm the generalization ability of mCTRL. Moreover, ablation studies and further analyses prove the effectiveness and efficiency of mCTRL and the specialization across aspects of generated embeddings.
期刊介绍:
Information Processing and Management is dedicated to publishing cutting-edge original research at the convergence of computing and information science. Our scope encompasses theory, methods, and applications across various domains, including advertising, business, health, information science, information technology marketing, and social computing.
We aim to cater to the interests of both primary researchers and practitioners by offering an effective platform for the timely dissemination of advanced and topical issues in this interdisciplinary field. The journal places particular emphasis on original research articles, research survey articles, research method articles, and articles addressing critical applications of research. Join us in advancing knowledge and innovation at the intersection of computing and information science.