Báo cáo khoa học: "Semantic classification of Chinese unknown words" pdf

... level 3 Figure 1 The taxonomy of the CiLin with the probabil- ity (partial) 3 Corpus analysis of Chinese unknown words 3.1 Definition of unknown words Unknown words are the Sinica Corpus ... the syntactic function of unknown words. Al- though proper nouns may contain lots of useful and valuable information in a sentence, the majority of unknown words in Ch...

Ngày tải lên: 31/03/2014, 03:20

... Over the set of 5 semantic rela- tions defined by Nastase and Szpakowicz (2003), they achieve an accuracy of 45.7% for the task of assigning one of 5 semantic relations to each of the 600 modifier-noun ... in this paper was twofold. Firstly, we wanted to compare the performance of different machine learning algorithms on the task of map- ping from a vector of web frequenc...

Ngày tải lên: 20/02/2014, 12:20

... Linguistics Improving Classification of Medical Assertions in Clinical Notes Youngjun Kim Ellen Riloff Stéphane M. Meystre School of Computing School of Computing Department of Biomedical Informatics ... Biomedical Informatics University of Utah University of Utah University of Utah Salt Lake City, UT Salt Lake City, UT Salt Lake City, UT youngjun@cs.utah.edu...

Ngày tải lên: 20/02/2014, 05:20

... Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions, pages 428–435, Sydney, July 2006. c 2006 ... Computational Linguistics 428 0.5 1 1.5 2 2.5 3 3.5 4 4.5 5 1 2 3 4 5 6 7 8 entropy offset 429 430 431 432 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 0.55 0.6 0.65 0.7 0.75

Ngày tải lên: 20/02/2014, 12:20

... the purpose of automatic tagging of the queries. We will define a set of probabilistic context-free rules, which generates bags (i.e. multi-sets) of words. Us- ing this new type of rule in ... the design and implementation of a parser for this kind of grammar. Section 5 gives an example of such a grammar designed for the purpose of automatic tagging of queries. Sectio...

Ngày tải lên: 08/03/2014, 00:20

... Evaluation Sophia Katrenko Institute of Informatics University of Amsterdam the Netherlands katrenko@science.uva.nl Pieter Adriaans Institute of Informatics University of Amsterdam the Netherlands pietera@science.uva.nl Abstract This ... 7 binary relations from the training set of the SemEval-2007 competition, all definitions of which share the re- quirement of the syntactic clos...

Ngày tải lên: 08/03/2014, 01:20

... good result both of DBA and SBA. The precision of DBA, the ratio of correct analyses to detected anal- yses, was 77% (=137/(137+19+21)); the re- call of DBA, the ratio of correct analyses ... information of nouns in an ordinary dictio- nary. 2 Semantic Roles of Nouns The meaning of a word can be recognized by the relationship with its semantic roles. In the case of...

Ngày tải lên: 08/03/2014, 06:20

... Evaluation of Chinese Translation Output: Word-Level or Character-Level? Maoxi Li Chengqing Zong Hwee Tou Ng National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of ... usually adopted as the smallest unit in most tasks of Chinese language processing. However, for automatic evaluation of the quali- ty of Chinese translation output...

Ngày tải lên: 17/03/2014, 00:20

... 1 Introduction The study of Chinese transliteration dates back to the seventh century when Buddhist scriptures were translated into Chinese. The earliest bit of Chinese translation theory ... into Chinese as 几何 /Ji-He/, which carries the pronunciation of geo- and expresses the meaning of “a science concerned with measuring the earth”. Many of the loanwords exist in...

Ngày tải lên: 17/03/2014, 04:20

... performance of constituent and dependency parsers. But the main purpose of our work is to apply the more sophisticated depen- dency parsing algorithms specifically to Chinese. Number of \in Train ... results for Chinese (see Table 3). 6 ilk.uvt.nl/conll/software/eval.pl Our finding does not contradict the main qualita- tive result of Cer et al. (2010), however, since the constituent...

Ngày tải lên: 23/03/2014, 14:20