Chinese-English mixed text normalization

Abstract

Along with the expansion of globalization, multilingualism has become a popular social phenomenon. More than one language may occur in the context of a single conversation. This phenomenon is also prevalent in China. A huge variety of informal Chinese texts contain English words, especially in emails, social media, and other user generated informal contents. Since most of the existing natural language processing algorithms were designed for processing monolingual information, mixed multilingual texts cannot be well analyzed by them. Hence, it is of critical importance to preprocess the mixed texts before applying other tasks. In this paper, we firstly analyze the phenomena of mixed usage of Chinese and English in Chinese microblogs. Then, we detail the proposed two-stage method for normalizing mixed texts. We propose to use a noisy channel approach to translate in-vocabulary words into Chinese. For better incorporating the historical information of users, we introduce a novel user aware neural network language model. For the out-of-vocabulary words (such as pronunciations, informal expressions and et al.), we propose to use a graph-based unsupervised method to categorize them. Experimental results on a manually annotated microblog dataset demonstrate the effectiveness of the proposed method. We also evaluate three natural language parsers with and without using the proposed method as the preprocessing step. From the results, we can see that the proposed method can significantly benefit other NLP tasks in processing mixed text.