Báo cáo khoa học: "Optimality Theory: Universal Grammar, Learning and Parsing Algorithms, and Connectionist Foundations" pot
Ngày tải lên: 31/03/2014, 06:20
... consists of a reparandum, an interruption point, and the alter- ation. The reparandum contains the words that the speaker means to replace, including both words that are in error and words that will ... Friday , there is an exact match of the word ‘to’ between reparandum and re- pair, and a part of speech match between the words ‘Boston’ and ‘Denver’. Another sort of structure in re...
Ngày tải lên: 20/02/2014, 09:20
... hear”, and (e) insert “from” between “hear” and “you.” These suggestions can be offered by learning the patterns rules related to “play ~ role” and “look forward” based on analysis of ngrams and ... and insertion (Step (4)) at i-indexed userUsage and j-indexed pattern. If the entries userUsage[i] and pattern[j] are equal literally (e.g., “VB” and “VB”) or gram- matical...
Ngày tải lên: 20/02/2014, 05:20
Tài liệu Báo cáo khoa học: "Limitations of Current Grammar Induction Algorithms" pptx
... (Vapnis and Cher- vonenkis) could then suffice. This, and other argu- ments favouring the use of machine learning tech- niques in linguistic theory testing, are very well re- viewed in Lappin and ... labelled), and only induce rules using the given tags. This kind of work is done by, for instance, Klein and Manning (2005). On the other hand, word-based models accept plain text as i...
Ngày tải lên: 20/02/2014, 12:20
Tài liệu Báo cáo khoa học: "Generating with a Grammar Based on Tree Descriptions: a Constraint-Based Approach" pptx
... summarises the parsing model presented in (Duchier and Thater, 1999) and Section 4 shows that this model can be extended to generate with DGs. In Section 5, we compare our generator with top-down and bottom-up ... section 2, two lexical lookup modules (one for parsing, one for generation) and a small DG fragment for English which has been tested in parsing and generation mode o...
Ngày tải lên: 20/02/2014, 18:20
Tài liệu Báo cáo khoa học: "Group Theory and Linguistic Processing*" doc
... sensitive to word order while retaining the hypothetical reasoning capabil- ities of standard (commutative) linear logic that make it so well-adapted to handling such phenomena as quanti- fier scoping ... grammars"), and argues that: • The standard group-theoretic notion of conjugacy, which is central in G-grammars, is well-suited to a uniform description of commutative and n...
Ngày tải lên: 20/02/2014, 18:20
Tài liệu Báo cáo khoa học: "Translating a Unification Grammar with Disjunctions into Logical Constraints" pdf
... on path equa- tions and lists of pairs of labels and values are better than those based on first-order terms in that the former is easier to describe and to understand. Parsing with term-based ... equations and lists of pairs of labels and values (Mukai and Yasukawa, 1985; Ai't-Kaci, 1986; Tsuda, 1994), and (ii) those that describe feature structures with first-ord...
Ngày tải lên: 20/02/2014, 18:20
Tài liệu Báo cáo khoa học: "D-Theory: Talking about Trees" pptx
... the standard referent of the analysis. (We further assume that the description produced by a D-theory parser will have at each stage of the analysis one and only one standard referent, and ... standard referent is a notion meaningful only to semantics. 132 The analysis of (6.2) proceeds as follows: After parsing "made" as a verb and "a mess" as its object...
Ngày tải lên: 21/02/2014, 20:20
Tài liệu Báo cáo khoa học: "STRING-TREE CORRESPONDENCE GRAMMAR: A DECLARATIVE GRAMMAR FORMALISM FOR DEFINING THE CORRESPONDENCE BETWEEN STRINGS OF TERMS AND TREE STRUCTURES" pdf
... a labeled tree, and the relation between a string of terms and a structural representation is defined as a mapping between elements of the set of substrings of the string and elements of the ... identifier and a label (eg. |:NP). To avoid a very messy diagram, in fig. l we have omitted the other subcorrespon- dence between substrings and subtrees, for example between the wh...
Ngày tải lên: 22/02/2014, 10:20
Báo cáo khoa học: "Sparsity in Dependency Grammar Induction" doc
... Section 2 and 3 review the models and sev- eral previous approaches for learning them. Sec- tion 4 describes learning with PR. Section 5 de- scribes experiments across 12 languages and Sec- tion ... Headden III et al. (2009). 3 Previous Learning Approaches In our experiments, we compare PR learning to standard expectation maximization (EM) and to Bayesian learning with a spa...
Ngày tải lên: 07/03/2014, 22:20