New Word Extraction from Chinese Financial Documents

With the tremendous development of data science, using unstructured documents to analyze marketing dynamics is attracting a great deal of attention. In this letter, we propose an iterative scheme to extract the new words, which is often a bottleneck for Chinese natural language processing (NLP) in financial markets analysis. In contrast to existing static features, the key novelty is the proposed dynamic features that characterize the similarity of context patterns. Via iteration, distinguishable seed context patterns are extracted. Tested on a 203 MB corpus, 19 291 words representing emerging industries, entities, projects, and products were extracted with a precision of 89.8% and recall of 88.9%, which outperforms most competitor methods.