... Japanese dependency parsing by using large-scale statistical information. It takes into account two kinds of informa- tion not considered in previous statistical (machine learning based) parsing ... ACL, pages 833–840, Sydney, July 2006. c 2006 Association for Computational Linguistics Japanese Dependency Parsing Using Co-occurrence Information and a Combination of Case Element...
Ngày tải lên: 20/02/2014, 12:20
... Matsumoto (2000; 2002), Sekine et al. (2000) for Japanese, Chung and Rim (2004) for Korean, Nivre et al. (2004) for Swedish, Nivre and Nilsson (2005) for Czech, among others. Dependency grammars represent the ... sentences by positing binary dependency relations between words. For instance, Figure 1 Figure 1: Dependency Relations for a Turkish and an English sentence shows t...
Ngày tải lên: 22/02/2014, 02:20
Tài liệu Báo cáo khoa học: " Mining the Web for Language Learning" pdf
... therefore cannot cover fresh words or new usages of existing words. Secondly, their search 1 http://www.engkoo.com. functions are often limited, making it hard for users to effectively find information ... NLP com- ponents, which conduct POS tagging, dependency parsing, and word alignment, respectively. It also includes components that learn translation informa- tion and collocations from...
Ngày tải lên: 20/02/2014, 05:20
Tài liệu Báo cáo khoa học: "A Modular Toolkit for Coreference Resolution" pdf
... application-internal representations to a suitable format for several machine learning toolkits: One module exposes the functionality of the the WEKA machine learning toolkit (Witten and Frank, 2005), ... rely on the surround- ing infrastructure for feature extraction and machine learning components. 3 Using BART Although BART is primarily meant as a platform for experimentation,...
Ngày tải lên: 20/02/2014, 09:20
Tài liệu Báo cáo khoa học: "Conditional Modality Fusion for Coreference Resolution" pdf
... because independent training of the modality-specific classi- fiers forces them to account for data that they can- not possibly explain. For example, if the speaker is not gesturing meaningfully, it ... different set of feature weights for each case: w v,1 when the non-verbal features are included, and w v,2 otherwise. The formal definition of the potential function for conditional modal...
Ngày tải lên: 20/02/2014, 12:20
Tài liệu Báo cáo khoa học: "Head-Driven Parsing for Word Lattices" ppt
... beam function, base beam value) for pars- ing using development test data consisting of strings for which we have annotated parse trees. The parsing accuracy for parsing word lattices was not directly ... the overparsing extension can be seen in Table 1. Each of the PARSEVAL measures improves when overparsing is used. 5.2 Parsing Lattices The success of the parsing model as a la...
Ngày tải lên: 20/02/2014, 15:21
Tài liệu Báo cáo khoa học: "REPRESENTATION OF TEXTS FOR INFORMATION RETRIEVAL" pdf
... TEXTS FOR INFORMATION RETRIEVAL N.J. Belkin, B.G. Michell, and D.G. Kuehner University of Western Ontario The representation of whole texts is a major concern of the field known as information ... following: a. A user, recognizing an information need, presents to an IR mechanism (i.e., a collection of texts, with a set of associated activities for representing, stor- ing, matching...
Ngày tải lên: 21/02/2014, 20:20
Tài liệu Báo cáo khoa học: "A LOGICAL SEMANTICS FOR FEATURE STRUCTURES" pdf
... satisfiability problem for CNF formulas of propositional logic can be reduced to the consistency (or satisfia- bility) problem for formulas in FML. Thus, the consistency problem for formulas in FML ... Greek alpha- bet axe used to stand for arbitrary formulas in FML. The formulas NIL and TOP axe intended to convey gno information z and ~inconsistent in- formation s respect...
Ngày tải lên: 21/02/2014, 20:20
Báo cáo khoa học: "Handling phrase reorderings for machine translation" pdf
... the av- erage accuracy for each reordering distance d. It shows that even for long distance reordering, the DPR model still performs well, while the MLE baseline usually performs badly (more than ... kinds of information extracted from the Input: The samples o, φ( ¯ f j , ¯e i ) N n=1 , step size η Initialization: k = 0; w o,k = 0 ∀o ∈ Ω; Repeat for n = 1, 2, . . . , N do for o ...
Ngày tải lên: 17/03/2014, 02:20
Báo cáo khoa học: "Generating Complex Morphology for Machine Translation" pdf
... framework, it is straightforward to encode the morphological properties of a word, in addition to its surface inflected form. For example, for a particular inflected word form y t and its con- text, ... USA hisamis@microsoft.com Abstract We present a novel method for predicting in- flected word forms for generating morpho- logically rich languages in machine trans- lation. We utilize a...
Ngày tải lên: 17/03/2014, 04:20