Báo cáo khoa học: "Chinese Verb Sense Discrimination Using an EM Clustering Model with Rich Linguistic Features" pot

... Chinese Verb Sense Discrimination Using an EM Clustering Model with Rich Linguistic Features Jinying Chen, Martha Palmer Department of Computer and Information Science University of Pennsylvania ... the verb “见|jian4” has one sense see, in which the verb typically takes a Human subject and a sentential complement, while in another sense show, the verb t...

Ngày tải lên: 08/03/2014, 04:22

... texts. In order to build up the model of the subject field, we need to perform a corpus-based semantic analysis. Prior to the semantic analysis, morpho-syntactic analysis is performed by LEXTER, ... 2) followed by a semi-automatic semantic analysis where automatic clustering techniques are used interactively by the knowledge engineer (see sections 3 and 4). We agree with the diff...

Ngày tải lên: 22/02/2014, 03:20

... work can be done by machine at the extreme conditions, say, without any assistance of human. We believe the performance of the existing Chinese segmenters, that is, the ability to deal with ... segmentation is the first step in any Chinese NLP system. This paper presents a new algorithm for segmenting Chinese texts without making use of any lexicon and hand-crafted linguistic resou...

Ngày tải lên: 20/02/2014, 18:20

... usages can use word sense dominance to assign senses to the different clusters generated. Sense dominance may be determined by sim- ple counting in sense- tagged data. However, dom- inance varies with ... bank’ with all of bank’s co-occurring words will be larger than the sum for any other sense. Dominance D I W of a sense or category (c) of the target word (t) is: D I W t c ∑ w T...

Ngày tải lên: 08/03/2014, 21:20

... (Magerman, 1996). Since another important, requirement of our prob- lem is to have small trees we have implemented a post-pruning technique. In a first step the tree is completely expanded and ... 1989) for a summary. Its most remarkable feature is that it can deal with any kind of constraints, thus the model can be improved by adding any constraints available and it makes the tagg...

Ngày tải lên: 08/03/2014, 21:20

... fan-out 1, we group it with a randomly chosen adjacent bundle with fan-out 2, which builds an expanded bundle with fan-out 2, which has a binary decomposition into the original bundle with fan-out ... backward quantities for the expanded range can be expressed as a function of the same quantities for r . There- fore if we store our quantities for previously pro- cessed ranges, each...

Ngày tải lên: 16/03/2014, 23:20

... than one WordNet sense, and 44 (1.1% of all annotated pages) received more than one Wikipedia sense. 2.3 Manual Annotation We implemented an annotation interface which stored all documents and ... Bunker R. T. 1993. A Semantic Concordance. In Proceedings of the ARPA WorkShop on Human Language Technol- ogy. San Francisco, Morgan Kaufman. M. Paramita, M. Sanderson, and P. Clough. 2009. Di-...

Ngày tải lên: 20/02/2014, 04:20

... dictionary of semantic frames is an essential element of natural language understanding systems that use ontologies. However, creating lexical resources that accurately capture semantic representations ... However, the semantic frames remain mostly hand-made in ResearchCyc 2 and non- existent in the open-license OpenCyc 3 . Translating VerbNet frames into Cyc will expand the natural...

Ngày tải lên: 20/02/2014, 04:20

... some attempts exploited WordNet to enrich queries with semantically-related terms. For in- stance, (Voorhees, 1994) manually expanded 50 queries over the TREC-1 collection using syn- onymy and other ... expansion was useful with short and in- complete queries, leaving the task of proper auto- matic expansion as an open problem. (Gonzalo et al., 1998) demonstrates an incre- ment in p...

Ngày tải lên: 20/02/2014, 12:20

... models SenseLearner definitions Word sense disambiguation Trained semantic models Sense tagged texts Figure 1: Semantic model learning in SENSE- LEARNER tagged texts, including SemCor, SENSEVAL data sets, and a corpus ... specifically identified in SemCor. 54 4 Semantic Models Different semantic models can be defined and trained for the disambiguation of different word categories. Althoug...

Ngày tải lên: 20/02/2014, 15:20