Semantic similarity is not enough: A novel NLP-based semantic similarity measure in context

被引:0
|
作者
Abbasi, Omid Reza [1 ]
Alesheikh, Ali Asghar [1 ]
Lotfata, Aynaz [2 ]
机构
[1] KN Toosi Univ Technol, Dept Geospatial Informat Syst, Tehran, Iran
[2] Univ Calif Davis, Sch Vet Med, Dept Pathol Microbiol & Immunol, Davis, CA 95616 USA
关键词
Computer science; Geographical information science; Machine learning;
D O I
10.1016/j.isci.2024.109883
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
In this study, we addressed two primary challenges: firstly, the issue of domain shift, which pertains changes in data characteristics or context that can impact model performance, and secondly, the discrepancy between semantic similarity and geographical distance. We employed topic modeling in conjunction with the BERT architecture. Our model was crafted to enhance similarity computations applied to geospatial text, aiming to integrate both semantic similarity and geographical proximity. We tested the model on two datasets, Persian Wikipedia articles and rental property advertisements. The findings demonstrate that the model effectively improved the correlation between semantic similarity and geographical distance. Furthermore, evaluation by real -world users within a recommender system context revealed notable increase in user satisfaction by approximately 22% for Wikipedia articles and 56% for advertisements.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] A semantic similarity measure in the context of semantic queries
    Blazquez-del-Toro, Jose M.
    Arias Fisteus, Jesus
    Luque Centeno, Vicente
    Sanchez-Fernandez, Luis
    INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS IN TECHNOLOGY, 2008, 33 (04) : 285 - 291
  • [2] Semantic Search and NLP-Based Diagnostics
    Kats, Yefim
    2014 IEEE 27TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), 2014, : 277 - 280
  • [3] A Novel Semantic Similarity Measure within Sentences
    Li, Yanni
    Li, Haisheng
    Cai, Qiang
    Han, Dongmei
    PROCEEDINGS OF 2012 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY (ICCSNT 2012), 2012, : 1176 - 1179
  • [4] A measure of semantic similarity between a reference context and a current context
    Guessoum, Djamel
    Miraoui, Moeiz
    Zaguia, Atef
    Tadj, Chakib
    JOURNAL OF AMBIENT INTELLIGENCE AND SMART ENVIRONMENTS, 2016, 8 (06) : 697 - 707
  • [5] CoMSS: Context based Measure for Semantic Similarity between Conceptual models
    Kaundal, Anjali
    Kaur, Arvinder
    2017 INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND CONTROL SYSTEMS (ICICCS), 2017, : 1080 - 1088
  • [6] News Summarization Based on Semantic Similarity Measure
    Yu, Hui
    HIS 2009: 2009 NINTH INTERNATIONAL CONFERENCE ON HYBRID INTELLIGENT SYSTEMS, VOL 1, PROCEEDINGS, 2009, : 180 - 183
  • [7] Context-based Image Semantic Similarity
    Franzoni, Valentina
    Leung, Clement H. C.
    Milani, Alfredo
    Pallottelli, Simonetta
    Li, Yuanxi
    2015 12TH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (FSKD), 2015, : 1280 - 1284
  • [8] A novel method to measure the semantic similarity of HPO terms
    Peng, Jiajie
    Xue, Hansheng
    Shao, Yukai
    Shang, Xuequn
    Wang, Yadong
    Chen, Jin
    INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS, 2017, 17 (02) : 173 - 188
  • [9] Embeddings Evaluation Using a Novel Measure of Semantic Similarity
    Anna Giabelli
    Lorenzo Malandri
    Fabio Mercorio
    Mario Mezzanzanica
    Navid Nobani
    Cognitive Computation, 2022, 14 : 749 - 763
  • [10] Embeddings Evaluation Using a Novel Measure of Semantic Similarity
    Giabelli, Anna
    Malandri, Lorenzo
    Mercorio, Fabio
    Mezzanzanica, Mario
    Nobani, Navid
    COGNITIVE COMPUTATION, 2022, 14 (02) : 749 - 763