The authors state an automatic method for semantic role labeling consistency calculation, based on the features of annotated corpus’ format, structure, content and user performances. The expriment shows that the proposed method is fast, stable and has high recall rate, and it can greatly improve the quality and efficiency.

Based on the triune Chinese function word usage knowledge base (CFKB), the rule-based method, CRF (conditional random field) model and GRU (gated recurrent unit) are adopted to automatically recognize the usages of auxiliary “DE”, and the accuracy rates are 34.4%, 77.5% and 81.3% respectively. In order to improve the accuracy, some usages of auxiliary “DE” are combined and formed coarse-grained usage. The accuracy of CRF achieves 81.8%, and the accuracy of neural network model achieves 84.5%. It is expected that the recognition result of auxiliary “DE” can improve the performance of other NLP task.

Based on 6.4 million chars of Chinese ancient poetry, the “Computer aided research system of Chinese ancient poems” provides a word-based analysis platform of Chinese ancient poems. More than 50000 Chinese words, including 40814 multi-char words, were extracted from the corpora via statistic method. Besides the full text retrieving function, the system also provide word-based statistic analysis, sentence based similarity retrieving, automatic Pinyin tagging and some other useful functions to benefit the profound analysis of the Chinese ancient poems. The National Social Science Foundation of China 1998-1999 funded the project.

It is necessary to grasp the main structure of the sentence through its predicate head for the sentence similarity calculation in EBMT. Taking 3000 tagged Chinese simple sentences as training set and the syntactic attributes and the contextual information as the classification features, this research acquires the knowledge of recognizing the predicate head through constructing a statistical decision tree model. The problem of applying the statistical decision tree to recognize the predicate head is also discussed.