Multilingual Argument Mining: Datasets and Analysis

被引:0
|
作者
Toledo-Ronen, Orith [1 ]
Orbach, Matan [1 ]
Bilu, Yonatan [1 ]
Spector, Artem [1 ]
Slonim, Noam [1 ]
机构
[1] IBM Res, Cambridge, MA 02142 USA
来源
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020 | 2020年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The growing interest in argument mining and computational argumentation brings with it a plethora of Natural Language Understanding (NLU) tasks and corresponding datasets. However, as with many other NLU tasks, the dominant language is English, with resources in other languages being few and far between. In this work, we explore the potential of transfer learning using the multilingual BERT model to address argument mining tasks in non-English languages, based on English datasets and the use of machine translation. We show that such methods are well suited for classifying the stance of arguments and detecting evidence, but less so for assessing the quality of arguments, presumably because quality is harder to preserve under translation. In addition, focusing on the translate-train approach, we show how the choice of languages for translation, and the relations among them, affect the accuracy of the resultant model. Finally, to facilitate evaluation of transfer learning on argument mining tasks, we provide a human-generated dataset with more than 10k arguments in multiple languages, as well as machine translation of the English datasets.
引用
收藏
页数:15
相关论文
共 50 条
  • [31] Text mining applied to multilingual corpora
    Neri, F
    Raffaelli, R
    Knowledge Mining, 2005, 185 : 123 - 131
  • [32] COMFO: Multilingual Corpus for Opinion Mining
    Faty, Lamine
    Drame, Khadim
    Sarr, Edouard Ngor
    Ndiaye, Marie
    Diop, Ibrahima
    Dia, Yoro
    Sall, Ousmane
    ARTIFICIAL GENERAL INTELLIGENCE, AGI 2022, 2023, 13539 : 14 - 19
  • [33] Mining the Multilingual Terminology from the Web
    Sadat, Fatiha
    2013 IEEE PACIFIC RIM CONFERENCE ON COMMUNICATIONS, COMPUTERS AND SIGNAL PROCESSING (PACRIM), 2013, : 41 - 45
  • [34] Multilingual sentence categorization and novelty mining
    Zhang, Yi
    Tsai, Flora S.
    Kwee, Agus Trisnajaya
    INFORMATION PROCESSING & MANAGEMENT, 2011, 47 (05) : 667 - 675
  • [35] Personalized multilingual Web content mining
    Chau, R
    Yeh, CH
    Smith, KA
    KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 1, PROCEEDINGS, 2004, 3213 : 155 - 163
  • [36] Multilingual Corpus Development for Opinion Mining
    Schulz, Julia Maria
    Womser-Hacker, Christa
    Mandl, Thomas
    LREC 2010 - SEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2010, : 3409 - 3412
  • [37] Text Mining for Automatic Lexical Analysis of Layman Text of Biomedical Argument
    Defilippi, D.
    Pivetti, S.
    Giacomini, M.
    WORLD CONGRESS ON MEDICAL PHYSICS AND BIOMEDICAL ENGINEERING, VOL 25, PT 12, 2009, 25 (12): : 281 - 284
  • [38] Towards an Argument Mining Pipeline Transforming Texts to Argument Graphs
    Lenz, Mirko
    Sahitaj, Premtim
    Kallenberg, Sean
    Coors, Christopher
    Dumani, Lorik
    Schenkel, Ralf
    Bergmann, Ralph
    COMPUTATIONAL MODELS OF ARGUMENT (COMMA 2020), 2020, 326 : 263 - 270
  • [39] Performance analysis of large language models in the domain of legal argument mining
    Al Zubaer, Abdullah
    Granitzer, Michael
    Mitrovic, Jelena
    FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2023, 6
  • [40] A Higher Order Mining Approach for the Analysis of Real-World Datasets
    Abghari, Shahrooz
    Boeva, Veselka
    Brage, Jens
    Grahn, Hakan
    ENERGIES, 2020, 13 (21)