Research on a Novel Word Co-occurrence Model and Its Application

@incollection{citeulike:2688376, abstract = {This paper presented a novel word co-occurrence model, which was based on an ontology representation of word sense. In this study, word sense ontology is firstly constructed by context multi-elements, and then, the usage of word co-occurrence in content was gotten in using part of speech, semantic, location, average co-occurrence transition probabilities, and was expressed as word co-occurrence feature; final, word cohesion is calculated to judge the co-occurrence degree by the same co-occurrence feature. The relation experiments in natural language processing acquire better results.}, author = {Zheng, Dequan and Zhao, Tiejun and Li, Sheng and Yu, Hao }, citeulike-article-id = {2688376}, doi = {10.1007/978-3-540-76719-0\_43}, journal = {Knowledge Science, Engineering and Management}, keywords = {distributional-similarity}, pages = {437--446}, posted-at = {2008-04-18 18:05:17}, priority = {3}, title = {Research on a Novel Word Co-occurrence Model and Its Application}, url = {http://dx.doi.org/10.1007/978-3-540-76719-0\_43}, year = {2007} }

TY - CHAP ID - citeulike:2688376 L3 - citeulike-article-id:2688376 TI - Research on a Novel Word Co-occurrence Model and Its Application JF - Knowledge Science, Engineering and Management SP - 437 EP - 446 N2 - This paper presented a novel word co-occurrence model, which was based on an ontology representation of word sense. In this study, word sense ontology is firstly constructed by context multi-elements, and then, the usage of word co-occurrence in content was gotten in using part of speech, semantic, location, average co-occurrence transition probabilities, and was expressed as word co-occurrence feature; final, word cohesion is calculated to judge the co-occurrence degree by the same co-occurrence feature. The relation experiments in natural language processing acquire better results. KW - distributional-similarity AU - Zheng, Dequan AU - Zhao, Tiejun AU - Li, Sheng AU - Yu, Hao PY - 2007/// UR - http://dx.doi.org/10.1007/978-3-540-76719-0_43 ER -