Báo cáo khoa học: "Learning Stochastic OT Grammars: A Bayesian approach using Data Augmentation and Gibbs Sampling" pptx
... 43rd Annual Meeting of the ACL, pages 346–353, Ann Arbor, June 2005. c 2005 Association for Computational Linguistics Learning Stochastic OT Grammars: A Bayesian approach using Data Augmentation ... a non -Bayesian perspective, the MCMC-based approach can be seen as a randomized strategy for learning a grammar. Computing resources make it possible to explore the en...
Ngày tải lên: 23/03/2014, 19:20
... These works annotated temporal relations between events and times, but low inter-annotator agreement made many TimeBank and TempEval tasks difficult (Boguraev and Ando, 2005; Verha- gen et al., 2007). ... should label returned-waiting with BEFORE since returned occurred first, and a causal classifier should label it CAUSAL since this and can be paraphrased as and as a result. We...
Ngày tải lên: 08/03/2014, 01:20
... countability prefer- ences of English nouns from unannotated corpora. We first annotate them automatically, and then train classifiers using a set of gold standard data, taken from COMLEX (Grishman ... determine NP and PP boundaries, and medium- recall chunk adjacency templates to recover inter- phrasal dependency. Third, we fully parse the data and simply read off all necessary...
Ngày tải lên: 17/03/2014, 06:20
Báo cáo khoa học: "Learning How to Conjugate the Romanian Verb. Rules for Regular and Partially Irregular Verbs" docx
... but not all and/ or not for the same person and number. 1. no alternation; a spera” (to hope); 2. alternation: ˘ a e for the 2nd person singular; a num ˘ ara” (to count); 3. no alternation; a ... ”d”; 18. alternation: ˘ a a for all forms except the 1st and 2nd person plural, d→z for the 2nd per- son singular due to palatalization; a c ˘ adea” (to fall); 19. no alternation; a veg...
Ngày tải lên: 17/03/2014, 22:20
Báo cáo khoa học: "LEARNING TRANSLATION SKILLS WITH A KNOWLEDGE-BASED FRENCH-ITALIAN CONJUNCTIONS IN CONTEXT" pdf
... of ELISA's research within a project of automatic translation, and for a better understanding and explanation of the student's misconceptions as well. Because the " ;a posteriori" ... education- al settings and in projects of natural language translation. Practically, our program is one of the few Intelligent Systems available in the field of Fo- reign La...
Ngày tải lên: 18/03/2014, 02:20
Báo cáo khoa học: "Learning to Extract Relations from the Web using Minimal Supervision" ppt
... appropriate for training datasets that contain just a few, very large bags. In a multi-instance kernel approach, only bags (and not instances) are considered as training examples, 577 which means that ... this may be an overestimate (w may appear in a sentence contain- ing a due to causes other than a) , and also because of data sparsity, the quantity τ(w) may sometimes result...
Ngày tải lên: 23/03/2014, 18:20
Báo cáo khoa học: "Learning Phrase-Based Spelling Error Models from Clickthrough Data" pot
... sen- tences, making a grammar-based approach inap- propriate. Most importantly, many queries con- tain search terms, such as proper nouns and names, which are not well established in the language. For ... q=harrypotter+sheme+park&aq=f&oq=&aqi= http://www.google.com/search? hl=en&ei=rnNAS8-oKsWe_AaB2eHlCA& sa=X&oi=spell&resnum=0&ct= result&cd=1&...
Ngày tải lên: 30/03/2014, 21:20
Báo cáo khoa học: "Learning to Tell Tales: A Data-driven Approach to Story Generation" doc
... of background knowledge contain- ing information about the story plot and its characters. This information is detailed and usually hand crafted. In this paper we propose a data- driven approach ... of learning methods for re- alizing each of these tasks automatically with- out much hand coding. For example, Duboue and McKeown (2002) and Barzilay and Lapata (2005) propose to lea...
Ngày tải lên: 30/03/2014, 23:20
Tài liệu Báo cáo khoa học: "Finding Hedges by Chasing Weasels: Hedge Detection Using Wikipedia Tags and Shallow Linguistic Features" doc
... corpus statistics and syntactic pat- terns. We take Wikipedia as an already annotated corpus using its tagged weasel words which mark sentences and phrases as non-factual. We evaluate the quality ... spe- cific weasel tag, so that Wikipedia can be viewed as a readily annotated corpus. Based on this data, we have built a system to detect sentences that contain linguistic hedges. We...
Ngày tải lên: 20/02/2014, 09:20
Báo cáo khoa học: Dissociation/association properties of a dodecameric cyclomaltodextrinase Effects of pH and salt concentration on the oligomeric state pot
... 5¢-AGTACATGTGGGACGTCAC CATGGAGTATGTCCC-3¢ (forward) and 5¢-GGGACAT ACTC CATGGTGACGTCCCACATGTACT-3¢ (reverse); for the H89V mutant, 5¢-TCTGCTGCAGCA GGGTGTT GAGAAGCGCTGGATG-3¢ (forward) and 5¢-CATCCAG CGCTTCTCAACACCCT ... indicated that separate dimers could form a dodecamer and that Fig. 1. Apparent molecular mass of CDase I-5 at various pH values determined by analytical ultracentrifu...
Ngày tải lên: 07/03/2014, 12:20