No abstract

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.

Knowledge‐enhanced short‐text matching has been a significant task attracting much attention in recent years. However, the existing approaches cannot effectively balance effect and efficiency. Effective models usually consist of complex network structures leading to slow inference speed and the difficulties of applications in actual practice. In addition, most knowledge‐enhanced models try to link the mentions in the text to the entities of the knowledge graphs—the difficulties of entity linking decrease the generalizability among different datasets. To address these problems, we propose a lightweight Semantic‐Enhanced Interactive Network (SEIN) model for efficient short‐text matching. Unlike most current research, SEIN employs an unsupervised method to select WordNet's most appropriate paraphrase description as the external semantic knowledge. It focuses on integrating semantic information and interactive information of text while simplifying the structure of other modules. We conduct intensive experiments on four real‐world datasets, that is, Quora, Twitter‐URL, SciTail, and SICK‐E. Compared with state‐of‐the‐art methods, SEIN achieves the best performance on most datasets. The experimental results proved that introducing external knowledge could effectively improve the performance of the short‐text matching models. The research sheds light on the role of lightweight models in leveraging external knowledge to improve the effect of short‐text matching.