Learning a Cross-Lingual Semantic Representation of Relations Expressed in Text

Rettinger, Achim; Schumilin, Artem; Thoma, Steffen; Ell, Basil

doi:10.1007/978-3-319-18818-8_21

Cited by 4 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that most of the current studies for the ERE task focus on exploiting mono-lingual data (e.g. in English), although cross-lingual learning has achieved great improvements on a variety of tasks, which include sentiment analysis (Ahmad et al , 2020; Deriu et al , 2017), information retrieval (Litschko et al , 2019), semantic role labelling (Mulcaire et al , 2018), question answering (Rettinger et al , 2015), dependency parsing (Tran and Bisazza, 2019), entity linking (Upadhyay et al , 2018) and so on. According to the essence of the knowledge which has been transferred between different languages, the cross-lingual paradigms could be categorized into three approaches, that is, instance/label transfer (Gfeller et al , 2016), model transfer (Fei et al , 2020) and representation transfer (Litschko et al , 2019; Masumura et al , 2018).…”

Section: Literature Reviewmentioning

confidence: 99%

Towards an entity relation extraction framework in the cross-lingual context

Xue

Wang

et al. 2021

View full text Add to dashboard Cite

Purpose Owing to the uneven distribution of annotated corpus among different languages, it is necessary to bridge the gap between low resource languages and high resource languages. From the perspective of entity relation extraction, this paper aims to extend the knowledge acquisition task from a single language context to a cross-lingual context, and to improve the relation extraction performance for low resource languages. Design/methodology/approach This paper proposes a cross-lingual adversarial relation extraction (CLARE) framework, which decomposes cross-lingual relation extraction into parallel corpus acquisition and adversarial adaptation relation extraction. Based on the proposed framework, this paper conducts extensive experiments in two tasks, i.e. the English-to-Chinese and the English-to-Arabic cross-lingual entity relation extraction. Findings The Macro-F1 values of the optimal models in the two tasks are 0.880 1 and 0.789 9, respectively, indicating that the proposed CLARE framework for CLARE can significantly improve the effect of low resource language entity relation extraction. The experimental results suggest that the proposed framework can effectively transfer the corpus as well as the annotated tags from English to Chinese and Arabic. This study reveals that the proposed approach is less human labour intensive and more effective in the cross-lingual entity relation extraction than the manual method. It shows that this approach has high generalizability among different languages. Originality/value The research results are of great significance for improving the performance of the cross-lingual knowledge acquisition. The cross-lingual transfer may greatly reduce the time and cost of the manual construction of the multi-lingual corpus. It sheds light on the knowledge acquisition and organization from the unstructured text in the era of big data.

show abstract