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
来源
PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP) | 2020年
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 55 条
[51]  
Yang ZY, 2019, 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019), P638
[52]  
Yeung CMA, 2011, LECT NOTES COMPUT SC, V6609, P377, DOI 10.1007/978-3-642-19437-5_31
[53]  
Zaidan Omar, 2007, NAACL-HLT 2007, P260
[54]  
Zhai Yuming, 2019, Towards Recognizing Phrase Translation Processes: Experiments on English-French
[55]  
Zhou WCS, 2019, 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), P3368