基于转换学习的词性标注分析-计算机应用技术专业论文.docxVIP

太原理 工大学硕士研究生学位论文 RESEARCH ON PART-OF-SPEECH TAGGING WITH TRANSFOR孔 t\TION-BASED LEARNING ABSTRACT As th e increasing information technology of society，the Internet is increasingly becoming a part of daily lì 缸， people are increasìngJy strong desire to communicate with the computer by natural language. But there i s a premi se that computers would understand naturaJ human Janguage. 丁his is a very challenging problem. This probJem is natural language processing problem ，and part of speech tagging is the most basic and important technology as the most low layer process in this field ，playing a key role to the whole language processmg. Part of speech tagging is wìdely used in many application areas，such as parsing，speech recognition ，text classification ，text-to-speech，information retrieval ，machine translation and other areas. MeanwhiJe ，with the rapid development of machine leaming algorithms ，a variety of machi ne learning methods have been appJied to the fìeld of speech tagging，HMM algorithm ， maximum entropy algorithm ，decision tree，rule-based algorithms and so on. The TBL algorithm is a kind of rule-based algorithm. Although the TBL algorithmhad been improved by many professors from 1995 and it is already mature relatively，the algorithm will take a lot of resources and performance to JJ) 二 IV IV 太原理 1.大字 硕、?析研究生学位论文 extract and estimate rules when it works. So the algorithm marked itself of own training relatively sJow. This thesis adopt the previous research ideas，on the basic of original algorithm ，we evaluate scores by skipping those ruJes that have a Jow evaluation score and didnt have a significant results to coφus annotation. Only the rules have a significant effect in application would be scored. First，fìnd the best transformation rules which can change the sampJe in the corpus，then find the context of the sample in the corpus，inOuence its context by these samples，and ul