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
  • [41] Fine-grained Co-Attentive Representation Learning for Semantic Code Search
    Deng, Zhongyang
    Xu, Ling
    Liu, Chao
    Yan, Meng
    Xu, Zhou
    Lei, Yan
    2022 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE ANALYSIS, EVOLUTION AND REENGINEERING (SANER 2022), 2022, : 396 - 407
  • [42] Category-specific Semantic Coherency Learning for Fine-grained Image Recognition
    Wang, Shijie
    Wang, Zhihui
    Li, Haojie
    Ouyang, Wanli
    MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, : 174 - 183
  • [43] Unsupervised Visual-Textual Correlation Learning With Fine-Grained Semantic Alignment
    Peng, Yuxin
    Ye, Zhaoda
    Qi, Jinwei
    Zhuo, Yunkan
    IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (05) : 3669 - 3683
  • [44] Question Answering through Transfer Learning from Large Fine-grained Supervision Data
    Min, Sewon
    Seo, Minjoon
    Hajishirzi, Hannaneh
    PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 2, 2017, : 510 - 517
  • [45] Learning Fine-Grained Cross Modality Excitement for Speech Emotion Recognition
    Li, Hang
    Ding, Wenbiao
    Wu, Zhongqin
    Liu, Zitao
    INTERSPEECH 2021, 2021, : 3375 - 3379
  • [46] Fine-grained similarity semantic preserving deep hashing for cross-modal retrieval
    Li, Guoyou
    Peng, Qingjun
    Zou, Dexu
    Yang, Jinyue
    Shu, Zhenqiu
    FRONTIERS IN PHYSICS, 2023, 11
  • [47] Adapting Fine-Grained Cross-View Localization to Areas Without Fine Ground Truth
    Xia, Zimin
    Shi, Yujiao
    Li, Hongdong
    Kooij, Julian F. P.
    COMPUTER VISION - ECCV 2024, PT XXXI, 2025, 15089 : 397 - 415
  • [48] FC-MTLF: A Fine- and Coarse-grained Multi-Task Learning Framework for Cross-Lingual Spoken Language Understanding
    Cheng, Xuxin
    Xu, Wanshi
    Yao, Ziyu
    Zhu, Zhihong
    Li, Yaowei
    Li, Hongxiang
    Zou, Yuexian
    INTERSPEECH 2023, 2023, : 690 - 694
  • [49] Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification
    Zhang, Bo
    Yuan, Jiakang
    Li, Baopu
    Chen, Tao
    Fan, Jiayuan
    Shi, Botian
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022, : 2135 - 2144
  • [50] From bird to sparrow: Learning-induced modulations in fine-grained semantic discrimination
    De Meo, Rosanna
    Bourquin, Nathalie M. -P.
    Knebel, Jean-Francois
    Murray, Micah M.
    Clarke, Stephanie
    NEUROIMAGE, 2015, 118 : 163 - 173