Constructing Uyghur Named Entity Recognition System Using Neural Machine Translation Tag Projection

Abstract

Although named entity recognition achieved great success by introducing the neural networks, it is challenging to apply these models to low resource languages including Uyghur while it depends on a large amount of annotated training data. Constructing a well-annotated named entity corpus manually is very time-consuming and labor-intensive. Most existing methods based on the parallel corpus combined with the word alignment tools. However, word alignment methods introduce alignment errors inevitably. In this paper, we address this problem by a named entity tag transfer method based on the common neural machine translation. The proposed method marks the entity boundaries in Chinese sentence and translates the sentences to Uyghur by neural machine translation system, hope that neural machine translation will align the source and target entity by the self-attention mechanism. The experimental results show that the Uyghur named entity recognition system trained by the constructed corpus achieve good performance on the test set, with 73.80% F1 score(3.79% improvement by baseline).

Chinese Named Entity Recognition Method for Domain-Specific Text

“…The domain NER technology is dependent on the NER's technology development. Early domain NER approaches used lexicon and rule-based pattern matching methods, e.g., some research scholars constructed a Uyghur personal name data dictionary for Uyghur NER [11], and if there are entities in the text that are not included in the dictionary, they are manually entered into the dictionary for the next recognition. Based on this, more accurate extraction of entities is achieved by constructing relevant rules, such as in the work of Li et al [12], where chemical substance name extraction is performed by constructing the rule of chemical + preposition + chemical prefix chemical symbol.…”