Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank

被引:0
|
作者
Briakou, Eleftheria [1 ]
Carpuat, Marine [1 ]
机构
[1] Univ Maryland, Dept Comp Sci, College Pk, MD 20742 USA
基金
美国国家科学基金会;
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
Detecting fine-grained differences in content conveyed in different languages matters for cross-lingual NLP and multilingual corpora analysis, but it is a challenging machine learning problem since annotation is expensive and hard to scale. This work improves the prediction and annotation of fine-grained semantic divergences. We introduce a training strategy for multilingual BERT models by learning to rank synthetic divergent examples of varying granularity. We evaluate our models on the Rationalized English-French Semantic Divergences, a new dataset released with this work, consisting of English-French sentence-pairs annotated with semantic divergence classes and token-level rationales. Learning to rank helps detect fine-grained sentence-level divergences more accurately than a strong sentence-level similarity model, while token-level predictions have the potential of further distinguishing between coarse and fine-grained divergences.
引用
收藏
页码:1563 / 1580
页数:18
相关论文
共 50 条
  • [1] Cross-lingual fine-grained entity typing
    Department of Computer Science, The University of Texas, Austin, United States
    arXiv, 1600,
  • [2] Cross-lingual text alignment for fine-grained plagiarism detection
    Ehsan, Nava
    Shakery, Azadeh
    Tompa, Frank Wm
    JOURNAL OF INFORMATION SCIENCE, 2019, 45 (04) : 443 - 459
  • [3] Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource Languages
    Han, Xu
    Luo, Yuqi
    Chen, Weize
    Liu, Zhiyuan
    Sun, Maosong
    Zhou, Botong
    Hao, Fei
    Zheng, Suncong
    PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 2241 - 2250
  • [4] Cross-lingual entity alignment based on complex relationships and fine-grained attributes
    Zhu, Beibei
    Tian, Ruijie
    Yuan, Osong
    Han, Ridong
    Yang, Yan
    Fu, Bo
    APPLIED SOFT COMPUTING, 2025, 172
  • [5] Curriculum-Style Fine-Grained Adaption for Unsupervised Cross-Lingual Dependency Transfer
    Guo, Peiming
    Huang, Shen
    Jiang, Peijie
    Sun, Yueheng
    Zhang, Meishan
    Zhang, Min
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2023, 31 : 322 - 332
  • [6] How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing?
    Jin, Hailong
    Dong, Tiansi
    Hou, Lei
    Li, Juanzi
    Chen, Hui
    Dai, Zelin
    Qu Yincen
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), 2022, : 3071 - 3081
  • [7] Enhancing low-resource cross-lingual summarization from noisy data with fine-grained reinforcement learning
    Huang, Yuxin
    Gu, Huailing
    Yu, Zhengtao
    Gao, Yumeng
    Pan, Tong
    Xu, Jialong
    FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING, 2024, 25 (01) : 121 - 134
  • [8] Fine-grained Coordinated Cross-lingual Text Stream Alignment for Endless Language Knowledge Acquisition
    Ge, Tao
    Dou, Qing
    Ji, Heng
    Cui, Lei
    Chang, Baobao
    Sui, Zhifang
    Wei, Furu
    Zhou, Ming
    2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), 2018, : 2496 - 2506
  • [9] A Learning to rank framework based on cross-lingual loss function for cross-lingual information retrieval
    Ghanbari, Elham
    Shakery, Azadeh
    APPLIED INTELLIGENCE, 2022, 52 (03) : 3156 - 3174
  • [10] A Learning to rank framework based on cross-lingual loss function for cross-lingual information retrieval
    Elham Ghanbari
    Azadeh Shakery
    Applied Intelligence, 2022, 52 : 3156 - 3174