Báo cáo khoa học: "Detecting Errors in Automatically-Parsed Dependency Relations" pot

Tài liệu Báo cáo khoa học: "Detecting Errors in Part-of-Speech Annotation" docx

Tài liệu Báo cáo khoa học: "Detecting Errors in Part-of-Speech Annotation" docx

... as well as linguistic intuition. Using this method, Kveain and Oliva (2002) report find- ing 2661 errors in the NEGRA corpus (containing 396,309 tokens). Interestingly, most of the errors found ... work Considering the significant effort that has been put into obtaining pos-tagged reference corpora in the past decade, there are surprisingly few pub- lications on the issue of detecting...

Ngày tải lên: 22/02/2014, 02:20

8 466 0
Báo cáo khoa học: "Detecting Errors in Discontinuous Structural Annotation" pdf

Báo cáo khoa học: "Detecting Errors in Discontinuous Structural Annotation" pdf

... shown in grey. 3 Being distinct means that each corpus position is only taken into account for the longest variation n-gram it occurs in. 2.2 Detecting variation in syntactic annotation In Dickinson ... a constituent, despite being in a nearly identical sen- tence. We would thus like to assign the discontinu- ous string sich einig in (5b) the label NIL, so that the labeling of thi...

Ngày tải lên: 17/03/2014, 06:20

8 187 0
Báo cáo khoa học: "Detecting Errors in Automatically-Parsed Dependency Relations" pot

Báo cáo khoa học: "Detecting Errors in Automatically-Parsed Dependency Relations" pot

... Linguistics, pages 729–738, Uppsala, Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics Detecting Errors in Automatically-Parsed Dependency Relations Markus Dickinson Indiana ... and dependency in- formation, a next step in evaluating and improv- ing the methods is to examine automatically POS- tagged data. Our methods should be able to find POS errors...

Ngày tải lên: 30/03/2014, 21:20

10 223 0
Báo cáo khoa học: "Correcting errors in speech recognition with articulatory dynamics" pot

Báo cáo khoa học: "Correcting errors in speech recognition with articulatory dynamics" pot

... split the data into 90% training and 10% testing sets for 5-cross validation. MOCHA and TORGO data are never combined in a single training set due to dif- fering EMA recording rates. In all cases, ... component takes into account var- ious physiological aspects of human speech production, including intergestural and in- terarticulator co-ordination and timing (Nam and Saltzman, 2003; Go...

Ngày tải lên: 16/03/2014, 23:20

9 322 0
Báo cáo khoa học: "Capturing Errors in Written Chinese Words" docx

Báo cáo khoa học: "Capturing Errors in Written Chinese Words" docx

... the time. 1 Introduction Incorrect writings in Chinese are related to our under- standing of the cognitive process of reading Chinese (e.g., Leck et al., 1995), to our understanding of why people ... special viewpoint in their minds – balancing the errors due to pronunciation and composition. 4 Reliability of Web-based Statistics In this section, we examine the effectiveness o...

Ngày tải lên: 17/03/2014, 02:20

4 264 0
Báo cáo khoa học: " Detecting Patterns in News Coverage of US Elections" pdf

Báo cáo khoa học: " Detecting Patterns in News Coverage of US Elections" pdf

... information con- cerning their role in the media narration of events. The interactive interface allows the users to retrieve news report supporting the relations of interest. 1 Introduction U.S presidential ... plot using the first two eigenvalues of the adjacency matrix, which seems to capture the main groupings in the politi- cal narrative. Future work will include making better use of t...

Ngày tải lên: 17/03/2014, 22:20

5 254 0
Báo cáo khoa học: "Detecting Compositionality in Multi-Word Expressions" doc

Báo cáo khoa học: "Detecting Compositionality in Multi-Word Expressions" doc

... simple words (Baldwin, 2006). Deciding idiomaticity of MWEs is highly impor- tant for machine translation, information retrieval, question answering, lexical acquisition, parsing and language generation. Compositionality ... which the meaning of a MWE can be predicted by com- bining the meanings of its components. Unlike syntactic compositionality (e.g. by and large), se- mantic compositional...

Ngày tải lên: 23/03/2014, 17:20

4 278 0
Báo cáo khoa học: "Correcting Errors in a Treebank Based on Synchronous Tree Substitution Grammar" pot

Báo cáo khoa học: "Correcting Errors in a Treebank Based on Synchronous Tree Substitution Grammar" pot

... method of correct- ing annotation errors in a treebank. By us- ing a synchronous grammar, the method transforms parse trees containing annota- tion errors into the ones whose errors are corrected. ... tree-to-tree transfor- mation. By using an STSG, our method trans- forms parse trees containing errors into the ones whose errors are corrected. The grammar is au- tomatically induce...

Ngày tải lên: 30/03/2014, 21:20

6 367 0
Báo cáo khoa học: "DETECTING PATTERNS IN ALEXICAL DATABASE" pdf

Báo cáo khoa học: "DETECTING PATTERNS IN ALEXICAL DATABASE" pdf

... role in defining sentences. The combination of these constraints carl be and actually is very useful, when trying to exploit the information contained in definitions, and when transforming ... definitions in which the word FORHA appears, only those defining something as "having the shape of something else". The implementation of these links allows to produce another...

Ngày tải lên: 31/03/2014, 17:20

4 229 0
Tài liệu Báo cáo khoa học: "Information Presentation in Spoken Dialogue Systems" potx

Tài liệu Báo cáo khoa học: "Information Presentation in Spoken Dialogue Systems" potx

... of interest for any rational user. All dominant options represent some tradeoff, but depending on the user’s interest, some of them are more interest- ing tradeoffs than others. Pruning dominated ... issue of giving the user a good overview of the option space, despite select- ing only the relevant options, by briefly accounting for the remaining (irrelevant) options. In the remainder of thi...

Ngày tải lên: 22/02/2014, 02:20

8 357 0
w