关键词: 信息抽取, 条件随机场, 引文信息, 论文头部信息

Abstract:

The information of headers and citations of research papers is necessaηfor many applications , such asthe field-based paper search , the paper statistics and the citation analysis. In order to enhance the utilization ofcontext features for information extraction which is greatly restricted by the hidden Markov model (HMM) , a methodbased on the conditional random fields (CRFs) is proposed to extract the information of paper header and citationfrom Chinese research papers. The proposed method , whose key is the parameter estimation and the feature selection, employs L-BFGS algorithm for the estimation of model parameters in the experiment and selects the categoriesfeatures of location , layout , lexicon and state transition as the feature set of the model. During the information extraction, the format information about list separators and special-labels is used to segment the text , and then CRFsare applied to the extraction in special fields. Experimental results show that the proposed method possesses betterperformance than that based on the HMM , and that the performance improvement varies with the features sets.

Key words: infoIτnation extraction, conditional random field, citation information, paper header information