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
  • [31] FGSI: distant supervision for relation extraction method based on fine-grained semantic information
    Chenghong Sun
    Weidong Ji
    Guohui Zhou
    Hui Guo
    Zengxiang Yin
    Yuqi Yue
    Scientific Reports, 13 (1)
  • [32] Cross-lingual multi-keyword rank search with semantic extension over encrypted data
    Guan, Zhitao
    Liu, Xueyan
    Wu, Longfei
    Wu, Jun
    Xu, Ruzhi
    Zhang, Jinhu
    Li, Yuanzhang
    INFORMATION SCIENCES, 2020, 514 : 523 - 540
  • [33] Joint Representation Learning of Cross-lingual Words and Entities via Attentive Distant Supervision
    Cao, Yixin
    Hou, Lei
    Li, Juanzi
    Liu, Zhiyuan
    Li, Chengjiang
    Chen, Xu
    Dong, Tiansi
    2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), 2018, : 227 - 237
  • [34] Multitask Learning for Cross-Lingual Transfer of Broad-coverage Semantic Dependencies
    Aminian, Maryam
    Rasooli, Mohammad Sadegh
    Diab, Mona
    PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 8268 - 8274
  • [35] Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding
    Chen, Tianshui
    Wu, Wenxi
    Gao, Yuefang
    Dong, Le
    Luo, Xiaonan
    Lin, Liang
    PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18), 2018, : 2023 - 2031
  • [36] Feature Learning by Distant Supervision for Fine-Grained Implicit Discourse Relation Identification
    Tang Y.
    Li Y.
    Liu L.
    Yu Z.
    Chen L.
    Beijing Daxue Xuebao (Ziran Kexue Ban)/Acta Scientiarum Naturalium Universitatis Pekinensis, 2019, 55 (01): : 91 - 97
  • [37] Cross-X Learning for Fine-Grained Visual Categorization
    Luo, Wei
    Yang, Xitong
    Mo, Xianjie
    Lu, Yuheng
    Davis, Larry S.
    Li, Jun
    Yang, Jian
    Lim, Ser-Nam
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 8241 - 8250
  • [38] Cross-media Deep Fine-grained Correlation Learning
    Zhuo Y.-K.
    Qi J.-W.
    Peng Y.-X.
    Ruan Jian Xue Bao/Journal of Software, 2019, 30 (04): : 884 - 895
  • [39] Cross-Part Learning for Fine-Grained Image Classification
    Liu, Man
    Zhang, Chunjie
    Bai, Huihui
    Zhang, Riquan
    Zhao, Yao
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 : 748 - 758
  • [40] Multi task learning with general vector space for cross-lingual semantic relation detection
    Sholikah, Rizka W.
    Arifin, Agus Z.
    Fatichah, Chastine
    Purwarianti, Ayu
    JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2022, 34 (05) : 2161 - 2169