Báo cáo khoa học: "Bypassed Alignment Graph for Learning Coordination in Japanese Sentences" doc
... Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 5–8, Suntec, Singapore, 4 August 2009. c 2009 ACL and AFNLP Bypassed Alignment Graph for Learning Coordination in Japanese Sentences Hideharu ... perceptron training. These features are assigned to the arcs of the alignment graph (or edit graph) originally developed for biological se- quence alignment. C...
Ngày tải lên: 08/03/2014, 01:20
... transform (HT) algorithm, in short, is to map all points of a line in the original space to a single accumulative value in the parameter space. We can describe a line on x-y plane in the form ... computational linguistics, including Dice coefficient (Kay and R6scheisen 1993), mutual information, ~2 (Gale and Church 1991b), dictionary and thesaurus Table 1. Linguistic constraint...
Ngày tải lên: 17/03/2014, 23:20
... English. For each language pair, we extracted grammar rules from the same data that were used for word alignment. The development data that were used for discriminative training were: for Chinese-English and ... combinations of the two top-scoring alignments (according to F1) in each di- rection, yielding four sets of alignments. Table 4 shows Bleu scores for translation models l...
Ngày tải lên: 30/03/2014, 17:20
Tài liệu Báo cáo khoa học: "An Improved Parser for Data-Oriented Lexical-Functional Analysis" doc
... corpus was divided into a 90% training set and a 10% test set. This division was random except for one constraint: that all the words in the test set actually occurred in the training set. The sentences ... 2000a). 5.4 Comparing Viterbi n best to Monte Carlo Finally, we were interested in comparing an alternative, more efficient search method for estimating the most probable analysi...
Ngày tải lên: 20/02/2014, 18:20
Tài liệu Báo cáo khoa học: "A Syntactic Framework for Speech Repairs and Other Disruptions" doc
... containing editing terms as constituents, whereas in our approach editing terms are separate utterances. 4In cases of overlapping utterances, it will take multiple interpretations (one for ... (a type of editing term) in expressing uncertainty and (Schober, 1999) describes how editing terms and speech repairs correlate with planning difficultly. Clearly this is information tha...
Ngày tải lên: 20/02/2014, 19:20
Báo cáo khoa học: "Employing Topic Models for Pattern-based Semantic Class Discovery" doc
... words in an ordi- nary document. In some sense, topic models are more suitable to be used here than in processing an ordinary document corpus. 3.3 Preprocessing and Postprocessing Preprocessing ... features for better performing the WSD task. In Boyd-Graber et al. (2007), Latent Dirichlet with WordNet (LDAWN) is developed for simultaneously disambiguating a corpus and learn...
Ngày tải lên: 08/03/2014, 00:20
Báo cáo khoa học: "Statistical Machine Translation for Query Expansion in Answer Retrieval" pptx
... p LM (syn I 1 ) λ LM For estimation of the feature weights λ defined in equation (4) we employed minimum error rate (MER) training under the BLEU measure (Och, 2003). Training data for MER training were ... practice imagination concentration information consciousness different meditation relaxation qa-translation (-): birth industrial induced induces paraphrasing (-): way workers induc...
Ngày tải lên: 08/03/2014, 02:21
Báo cáo khoa học: "A Nonparametric Method for Extraction of Candidate Phrasal Terms" docx
... falling off rapidly as larger portions 605 of the n-best list were included, but they report better performance with statistical and information theoretic measures (including mutual information) ... Technology: Domain Description and Content Characterization. Natural Language Engineering 5(1):17-44. Choueka, Y. (1988). Looking for needles in a haystack or locating interesting collo...
Ngày tải lên: 08/03/2014, 04:22
Báo cáo khoa học: "Machine-learned contexts for linguistic operations in German sentence realization" doc
... a machine Computational Linguistics (ACL), Philadelphia, July 2002, pp. 25-32. Proceedings of the 40th Annual Meeting of the Association for learning approach. The linguistically informed ... complex linguistic phenomena, while machine learning automates the discovery of contexts that are linguistically relevant and relevant for the domain of the data. The machine learning ap...
Ngày tải lên: 08/03/2014, 07:20
Báo cáo khoa học: "Semantic Information Preprocessing for Natural Language Interfaces to Databases" docx
... provides a formalism for describing how a formula consisting of lexical predicates can be tranlsated into formula consisting of database predicates. The information used in the translation ... time. For each predicate in the formula Fting, there is a so-called conjunctive context that consists of conjuncts occurring together with the predicate in Fting, meaning postulates...
Ngày tải lên: 08/03/2014, 07:20