Abstract:
This paper presents an approach of building a contemporary Chinese dictionary on constituent structure of compounds. Manual tagging and three automatic tagging methods, i...Show MoreMetadata
Abstract:
This paper presents an approach of building a contemporary Chinese dictionary on constituent structure of compounds. Manual tagging and three automatic tagging methods, including bi-direction parallel analogy, paired parallel analogy and inferring based on the consistency between form and meaning, are used. More than 40,000 words of all the 54000 bi-syllabic words in Hownet are fully or half semantically tagged by these three automatic methods. In the process of manual tagging, the difficulties and corresponding solving schemes are also presented in this paper. After manual and automatic tagging, two methods are used for checking their results. First, several heuristic rules are used on manual tagging results to mine abnormal tagging. Second, the manual and automatic tagging results are comparing with each other and the inconsistent tagging results are also considered as abnormal tagging. All abnormal tagging results are reserved for further checking.
Published in: 2009 International Conference on Natural Language Processing and Knowledge Engineering
Date of Conference: 24-27 September 2009
Date Added to IEEE Xplore: 06 November 2009
ISBN Information: