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
  • [21] Learning Cross-lingual Distributed Logical Representations for Semantic Parsing
    Zou, Yanyan
    Lu, Wei
    PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2, 2018, : 673 - 679
  • [22] Semantic interaction learning for fine-grained vehicle recognition
    Zhang, Jingjing
    Lei, Jingsheng
    Yang, Shengying
    Yang, Xinqi
    COMPUTER ANIMATION AND VIRTUAL WORLDS, 2022, 33 (01)
  • [23] Query-dependent learning to rank for cross-lingual information retrieval
    Elham Ghanbari
    Azadeh Shakery
    Knowledge and Information Systems, 2019, 59 : 711 - 743
  • [24] Query-dependent learning to rank for cross-lingual information retrieval
    Ghanbari, Elham
    Shakery, Azadeh
    KNOWLEDGE AND INFORMATION SYSTEMS, 2019, 59 (03) : 711 - 743
  • [25] Combining Cross-lingual and Cross-task Supervision for Zero-Shot Learning
    Pikuliak, Matus
    Simko, Marian
    TEXT, SPEECH, AND DIALOGUE (TSD 2020), 2020, 12284 : 162 - 170
  • [26] Fine-grained label learning in object detection with weak supervision of captions
    Wang, Xue
    Du, Youtian
    Verberne, Suzan
    Verbeek, Fons J.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (05) : 6557 - 6579
  • [27] Fine-grained label learning in object detection with weak supervision of captions
    Xue Wang
    Youtian Du
    Suzan Verberne
    Fons J. Verbeek
    Multimedia Tools and Applications, 2023, 82 : 6557 - 6579
  • [28] FGSI: distant supervision for relation extraction method based on fine-grained semantic information
    Sun, Chenghong
    Ji, Weidong
    Zhou, Guohui
    Guo, Hui
    Yin, Zengxiang
    Yue, Yuqi
    SCIENTIFIC REPORTS, 2023, 13 (01):
  • [29] Beyond MeSH: Fine-grained semantic indexing of biomedical literature based on weak supervision
    Nentidis, Anastasios
    Krithara, Anastasia
    Tsoumakas, Grigorios
    Paliouras, Georgios
    INFORMATION PROCESSING & MANAGEMENT, 2020, 57 (05)
  • [30] Beyond MeSH: Fine-Grained Semantic Indexing of Biomedical Literature based on Weak Supervision
    Nentidis, Anastasios
    Krithara, Anastasia
    Tsoumakas, Grigorios
    Paliouras, Georgios
    2019 IEEE 32ND INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), 2019, : 180 - 185