Báo cáo khoa học: "Bootstrapping a Stochastic Transducer for Arabic-English Transliteration Extraction" pdf

... 2002) or (AbdulJaleel and Larkey, 2003) require a large set of sample transliterations to use for training. If such a training set is unavailable for a particular language pair, a detection algorithm ... 2E8 {tarek,kondrak}@cs.ualberta.ca Abstract We propose a bootstrapping approach to training a memoriless stochastic transducer for the task of extracting transliteration...

Ngày tải lên: 08/03/2014, 02:21

... and retrieval Marita Ailomaa, Miroslav Melichar, Martin Rajman Artificial Intelligence Laboratory ´ Ecole Polytechnique F ´ ed ´ erale de Lausanne CH-1015 Lausanne, Switzerland marita.ailomaa@epfl.ch Agnes ... more familiar – modality for a sizeable portion of the experiment. In order to gather a useful amount of natural language data, greater care has to be taken to design the system in...

Ngày tải lên: 20/02/2014, 12:20

... with grammars and language resource management. All Language Resources are structured in XML formats, as well as binary formats more adequate to efficient processing; the required format con- verters ... automata (automata that call other automata). The termi- nal symbols are lexical masks (Blanc and Dister, 2004), which are underspecified word tags i.e. that represent a set of tagged words m...

Ngày tải lên: 20/02/2014, 12:20

... here allows for a balanced extension of this very smaU core. The list//3 was chosen as the statistical core vocabulary serving as a base for applying se- mantic criteria, becat, se the overall ... claim that one can achieve a fixed point from where on no new words are added to tim set, and that at this moment one has reached a rather good approximation to a semantic core...

Ngày tải lên: 22/02/2014, 10:20

... Minneapolis” that he actu- ally is from Minnesota. 5 Evaluation measures The evaluation measures will compare a set of clusters to a set of classes. An ideal evaluation measure should reward a set ... almost paraphrases. For our task sentences that are not paraphrases can be in the same cluster (see rule 5, 8, 9). In general there are several constraints that pull against each other....

Ngày tải lên: 08/03/2014, 01:20

... meanings for those same data. For the sec- ond and third tasks, we train a semantic parser on the automatically disambiguated data, and test on sen- tences from the third, unseen map. For all ... The remain- ing refined landmarks plans are then treated as su- pervised training data for a semantic-parser learner, KRISP (Kate and Mooney, 2006). Once a seman- tic parser is trained,...

Ngày tải lên: 19/02/2014, 19:20

... European Chapter of the Association for Computational Linguistics, pages 11–15, Avignon, France, April 23 - 27 2012. c 2012 Association for Computational Linguistics Collaborative Machine Translation ... mathematical for- mulas, chemical compounds, pseudo-code, and enriched with domain bilingual terminology (see Section 2). Large amounts of monolingual and parallel data are available t...

Ngày tải lên: 22/02/2014, 03:20

... ambiguous name or is an alternative name, instead of a canonical name. CATEGORY. Category objects represent Wikipedia categories and allow access to the ar- ticles within each category. As categories ... is a page that represents either a normal Wikipedia article, a redirect to an article, or a disambiguation page. Each page object provides access to the article text (with m...

Ngày tải lên: 08/03/2014, 01:20

... Tsubouchi H, Naka D, Takahashi K, Okigaki M, Arakaki N, Nakayama H, Hirono S, Sakiy- ama O, Takahashi K et al. (1989) Molecular cloning and sequence analysis of cDNA for human hepatocyte growth factor. ... Yokohama, Japan 2 Advanced Medical Research Laboratory, Mitsubishi Tanabe Pharma Corporation, Kamoshida-cho, Aoba-ku, Yokohama, Japan Introduction Type II transmembrane serine proteases (...

Ngày tải lên: 15/02/2014, 01:20

... from bacterial genomics. Nat Prod Rep 24, 1073–1109. 32 Umezawa H, Aoyagi T, Ogawa K, Obata T, Iinuma H, Naganawa H, Hamada M & Takeuchi T (1985) For- oxymithine, a new inhibitor of angiotensin-converting enzyme, ... (Hartmann Analytic, Braunschweig, Germany) was added. The supernatants were extracted with XAD16 resin after an additional 2 days of growth. The dried eluate was dissolve...

Ngày tải lên: 16/02/2014, 09:20