Báo cáo khoa học: "Parsing the WSJ using CCG and Log-Linear Models" pptx

Báo cáo khoa học: "Parsing the WSJ using CCG and Log-Linear Models" pptx

Báo cáo khoa học: "Parsing the WSJ using CCG and Log-Linear Models" pptx

... word of the lex- ical category, f is the lexical category, s is the argu- ment slot, h a is the head word of the argument, and l indicates whether the dependency is long-range. For example, the long-range ... and the empirical expected value, of each feature (to calcu- late the gradient); and the value of the likelihood function. For the normal-form model, the...

Ngày tải lên: 23/03/2014, 19:20

8 336 0
Báo cáo khoa học: "Comparing the Accuracy of CCG and Penn Treebank Parsers" docx

Báo cáo khoa học: "Comparing the Accuracy of CCG and Penn Treebank Parsers" docx

... accuracy of the CCG parser. Results are calcu- lated using both gold standard and automatically assigned POS tags; # is the number of sentences in the sample, and the % column gives the sample size ... as a percentage of the whole section. We compare the CCG parser to the Berkeley parser using the accurate mode of the Berke- ley parser, together with the mode...

Ngày tải lên: 17/03/2014, 02:20

4 369 0
Báo cáo khoa học: " Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques" doc

Báo cáo khoa học: " Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques" doc

... purposes using the WSJ treebank, the grammar was modified to parse part of speech tags and labeled bracketing. A stripped down ver- sion of the WSJ treebank was created that used only those POS tags and ... grammatical relations. The WSJ la- beled brackets are given LFG lexical entries which constrain both the c-structure and the f-structure of the parse. For exampl...

Ngày tải lên: 23/03/2014, 20:20

8 477 0
Báo cáo khoa học: "Parsing the Internal Structure of Words: A New Paradigm for Chinese Word Segmentation" doc

Báo cáo khoa học: "Parsing the Internal Structure of Words: A New Paradigm for Chinese Word Segmentation" doc

... standards in the hope of saving some expensive human labor. We believe the best solution to the problem of divergent standards and requirements is to annotate and analyze word struc- tures. Then ... L i , R i and H are lexicalized nonterminals and H is the head. To generate this constituent, first P is generated, then the head child H is generated conditioned on P , and fina...

Ngày tải lên: 17/03/2014, 00:20

10 476 0
Báo cáo khoa học: "Parsing with Treebank Grammars: Empirical Bounds, Theoretical Models, and the Structure of the Penn Treebank" ppt

Báo cáo khoa học: "Parsing with Treebank Grammars: Empirical Bounds, Theoretical Models, and the Structure of the Penn Treebank" ppt

... NN:[2,3]) 3.1 Time The parser has an theoretical time bound, where is the number of words in the sentence to be parsed, is the number of nonterminal categories in the grammar and is the number of ... are present, and greater than 2.0 when they are not. With unaries, the linear terms in the reduced equation are significant over these sentence lengths and drag down the ex...

Ngày tải lên: 17/03/2014, 07:20

8 405 0
Báo cáo khoa học: "PARSING THE LOB CORPUS" pdf

Báo cáo khoa học: "PARSING THE LOB CORPUS" pdf

... varying the queuing placement and the definition of when a parse is finished, the efficiency and ac- curacy of the parser can be radically altered. The parser orders these new rules and phrases ... " ;The pastry chef placed the pie in the oven." In the figure, items to the left of the vertical line are the phrases and rules popped off the stack. To...

Ngày tải lên: 31/03/2014, 18:20

9 301 0
Báo cáo khoa học: "Parsing the Wall Street Journal with the Inside-Outside Algorithm" potx

Báo cáo khoa học: "Parsing the Wall Street Journal with the Inside-Outside Algorithm" potx

... of the available training material ,and evaluate the effect of the training size on the bracketing perform,'mce. Then, we describe a method for reducing the number of parameters in the ... set randomly while maintaining the proper conditions for stochastic context-free grammars. 1 Using the algorithm described in Pereira and Schabes (1992), the current rule pr...

Ngày tải lên: 01/04/2014, 00:20

7 573 0
Tài liệu Báo cáo khoa học: "Untangling the Cross-Lingual Link Structure of Wikipedia" pptx

Tài liệu Báo cáo khoa học: "Untangling the Cross-Lingual Link Structure of Wikipedia" pptx

... = 1 nq ˆc f +  v∈S ˆc(v, r) (2) The first summand accounts for the edges en- tirely within the region, and the second one ac- counts for the edges in C(v, r) to the extent that they are within the radius. The definition ... of the LP. The properties of this algorithm are given by the following two theorems (proofs in Appendix A). Theorem 2. The algorithm yields a vali...

Ngày tải lên: 20/02/2014, 04:20

10 542 1
Tài liệu Báo cáo khoa học: "Understanding the Semantic Structure of Noun Phrase Queries" pptx

Tài liệu Báo cáo khoa học: "Understanding the Semantic Structure of Noun Phrase Queries" pptx

... time IM:Title the godfather Other the, in, that Other the, in, that Other the, in, that Table 3: Label sets and their respective query segment examples for the intent class Movie, Job and National ... on the attributes of an intent class. For example, there are two constraints implied in the query “alice in wonderland 2010 cast”: (1) the Title of the movie is “alice in wond...

Ngày tải lên: 20/02/2014, 04:20

9 675 0
Tài liệu Báo cáo khoa học: "REAPING THE BENEFITS OF INTERACTIVE AND SEMANTICS*" pdf

Tài liệu Báo cáo khoa học: "REAPING THE BENEFITS OF INTERACTIVE AND SEMANTICS*" pdf

... semantics. ASLC, on the other hand, does not attempt to at- tach the VP to the S until the very end (Fig lb). Thus even the thematic role of the subject NP re- mains unresolved until the very end. ... COMMUNICATE The content of the communication between syntax and semantics is a set of grammatical relations and thematic roles. Syntax talks about the grammati- cal...

Ngày tải lên: 20/02/2014, 21:20

3 418 0
w