Báo cáo khoa học: "A Bag of Useful Techniques for Efficient and Robust Parsing" ppt

Báo cáo khoa học: "A Bag of Useful Techniques for Efficient and Robust Parsing" ppt

Báo cáo khoa học: "A Bag of Useful Techniques for Efficient and Robust Parsing" ppt

... A Bag of Useful Techniques for Efficient and Robust Parsing Bernd Kiefer t, Hans-Ulrich Kriegert, John Carroll $, and Rob Malouff IGerman Research Center for Artificial Intelligence ... $Cognitive and Computing Sciences, University of Sussex Falmer, Brighton BN1 9QH, UK *Center for the Study of Language and Information, Stanford University Ventura Hall, Sta...

Ngày tải lên: 08/03/2014, 06:20

8 340 0
Báo cáo khoa học: "A Comparison of Chinese Parsers for Stanford Dependencies" ppt

Báo cáo khoa học: "A Comparison of Chinese Parsers for Stanford Dependencies" ppt

... only and exclude gen- eration of basic Stanford dependencies (for constituent parsers) and part -of- speech tagging (for dependency parsers). 3 Results Table 3 tabulates efficiency and performance for ... 3: Performance and efficiency for all parsers on CTB data: unlabeled and labeled attachment scores (UAS/LAS) are for both development and test data sets; parsing times (m...

Ngày tải lên: 23/03/2014, 14:20

6 460 0
Báo cáo khoa học: "A Class of Submodular Functions for Document Summarization" pot

Báo cáo khoa học: "A Class of Submodular Functions for Document Summarization" pot

... in Neural Information Processing Systems. J. Carbonell and J. Goldstein. 1998. The use of MMR, diversity-based reranking for reordering documents and producing summaries. In Proc. of SIGIR. A. ... Takamura and M. Okumura. 2009. Text summariza- tion model based on maximum coverage problem and its variant. In Proceedings of the 12th Conference of the European Chapter of the...

Ngày tải lên: 23/03/2014, 16:20

11 440 0
Báo cáo khoa học: "A Figure of Merit Technique for the Resolution of Non-Grammatical Ambiguity" ppt

Báo cáo khoa học: "A Figure of Merit Technique for the Resolution of Non-Grammatical Ambiguity" ppt

... BUILDING(s) (of) ONE/ALONE (of) DOUBLE/GEMINATE (of) ANNUAL/YEARS (of) LAYER/LAMELLA (of) (to /for) (by/with/as) LINE (of) THIN-CRUST(s) HOW/AS/BUT (of) (to /for) (by/with/as) FOSSILIZED (of) (to /for) - ... words" for the sake of simplicity. The target equivalents of the single meaning words have different degrees of probability of occurrence in the different fields...

Ngày tải lên: 30/03/2014, 17:20

5 299 0
Báo cáo khoa học: "A Comparison of Event Models for Naive Bayes Anti-Spam E-Mail Filtering" potx

Báo cáo khoa học: "A Comparison of Event Models for Naive Bayes Anti-Spam E-Mail Filtering" potx

... the document. From a linguistic point of view, a document is made up of words, and the semantics of the doc- ument is determined by the meaning of the words and the linguistic structure of the document. The Naive ... cases, precision and recall were differ- ent over the entire range of the number of selected words. In these cases we give the recall and accu- racy for t...

Ngày tải lên: 31/03/2014, 20:20

8 514 0
Báo cáo khoa học: "A Logic of Semantic Representations for Shallow Parsing" pdf

Báo cáo khoa học: "A Logic of Semantic Representations for Shallow Parsing" pdf

... a 41 to the first child of that node (i.e. the node 21, labelled with “fat”) and a 42 to the node 22, and so forth. g will map x 1 and x 3 to x, and x 6 and x 7 to y, and so on. And σ will map each ... of choices for the subsets S  in condition 2 of Def. 7, and there is only a finite set of choices of new dom- inance atoms that satisfy condition 3. Therefore, the se...

Ngày tải lên: 31/03/2014, 20:20

9 312 0
Tài liệu Báo cáo khoa học: Structural features of proinsulin C-peptide oligomeric and amyloid states pptx

Tài liệu Báo cáo khoa học: Structural features of proinsulin C-peptide oligomeric and amyloid states pptx

... and a wide range of spectroscopic techniques. Suitable methods for investigation of the secondary structure and morphology of such structures, however, require the presence of large amounts of ... conditions (B), and of 100 l M C-peptide in the presence of insulin (C) and of 100 l M C-peptide in the presence of NaCl and formamide (D) under native conditions. J....

Ngày tải lên: 18/02/2014, 04:20

10 562 0
Tài liệu Báo cáo khoa học: "The Use of Shared Forests in Tree Adjoining Grammar Parsing" pptx

Tài liệu Báo cáo khoa học: "The Use of Shared Forests in Tree Adjoining Grammar Parsing" pptx

... state set of of Me,. IIow- ever, unlike the case of the cfg shared forest gram- mar, the extraction of individual parses for the input w does not simply involve reading off a derivation of Gw. ... intersection of L(G) and L(Mw). P includes the following set of productions for the start symbol S' iS'[] , (T, qo, q/)[r/] I q; e F and t/is root of initi...

Ngày tải lên: 22/02/2014, 10:20

10 554 0
Báo cáo khoa học: "A Probabilistic Context-free Grammar for Disambiguation in Morphological Parsing" pdf

Báo cáo khoa học: "A Probabilistic Context-free Grammar for Disambiguation in Morphological Parsing" pdf

... as most likely member of a set of alternatives for 92% of the test words. For a proper judgement of this performance, the percentage must be compared with the chances of selecting the most ... complete and more reliable, but as a result of these problems, the collection of fre- quency information became a time-consuming and error-sensitive job: a lot of work had...

Ngày tải lên: 18/03/2014, 02:20

10 435 0
Báo cáo khoa học: "A Joint Rule Selection Model for Hierarchical Phrase-based Translation" pptx

Báo cáo khoa học: "A Joint Rule Selection Model for Hierarchical Phrase-based Translation" pptx

... clues from the rich context infor- mation. 3 Model Training of CBSM and CBTM 3.1 The acquisition of training instances CBSM and CBTM are trained by ME approach for the binary classification, where ... constructed for the training of CBSM and CBTM. Let s and t be the source sentence and target sentence, W be the word alignment between them, r s be a source-side rule that pat...

Ngày tải lên: 23/03/2014, 16:20

6 314 0
w