Improving Loanword Identification in Low‐Resource Language with Data Augmentation and Multiple Feature Fusion

Abstract

Loanword identification is studied in recent years to alleviate data sparseness in several natural language processing (NLP) tasks, such as machine translation, cross-lingual information retrieval, and so on. However, recent studies on this topic usually put efforts on high-resource languages (such as Chinese, English, and Russian); for low-resource languages, such as Uyghur and Mongolian, due to the limitation of resources and lack of annotated data, loanword identification on these languages tends to have lower performance. To overcome this problem, we first propose a lexical constraint-based data augmentation method to generate training data for low-resource language loanword identification; then, a loanword identification model based on a log-linear RNN is introduced to improve the performance of low-resource loanword identification by incorporating features such as word-level embeddings, character-level embeddings, pronunciation similarity, and part-of-speech (POS) into one model. Experimental results on loanword identification in Uyghur (in this study, we mainly focus on Arabic, Chinese, Russian, and Turkish loanwords in Uyghur) showed that our proposed method achieves best performance compared with several strong baseline systems.

TBR-NER: Research on COVID-19 Text Information Extraction Based on Joint Learning of Topic Recognition and Named Entity Recognition

“…that synthesizes new data from existing data. When training samples are sparse and labeling costs are high, it seeks to enhance the number of data points, reduce overfitting, and improve the model's overall generalization ability [18,19].…”

“…In December 2019, a novel coronavirus (COVID- 19) was transmitted between species and spread fast worldwide in a short period. The fast spread of the disease and severe economic and social devastation are far beyond people's expectations.…”