Báo cáo khoa học: "ALIGNING A PARALLEL ENGLISH-CHINESE CORPUS STATISTICALLY WITH LEXICAL CRITERIA" doc

... perfor- mance of WSD algorithms for languages such as English for which hand-crafted sense-annotated corpora have been available (Agirre et al., 2007; Erk and Strapparava, 2012; Mihalcea et al., ... amount of data that can reasonably be annotated by hand. Leacock et al. (1998), Agirre and Lopez de La- calle (2004), and Mihalcea and Moldovan (1999) propose a set of methods for automatic harv...

Ngày tải lên: 22/02/2014, 03:20

... available in machine-readable form. We have obtained and converted these materials by special arrangement. The materials contain high-quality literal translation. Statements in LegCo may ... be made using either English or Cantonese, and are tran- scribed in the original language. A translation to the other language is made later to yield com- plete parallel texts, with annotati...

Ngày tải lên: 17/03/2014, 09:20

... each paid reward. • Qualifications To improve the data quality, a HIT can also be attached to certain tests, “qualifications” that are either system-provided or created by the requester. An example ... both answers. We calculated the overall average agreement ratio (Total Avg) and the average of the best matches between two assignments within one HIT (Best Match). We ran the test for two data...

Ngày tải lên: 20/02/2014, 09:20

... interpretation is available for each syntactic node. This is guaranteed by the seman- tic rule formalism and by the fact that every lexical item has a semantics associated with it. Table 2 contains ... example, the various categorial unification ap- proaches, such as Unification Categorial Gram- mar (Zeevat, Klein, and Calder, 1987)). Even when a syntactic skeleton is assumed,...

Ngày tải lên: 20/02/2014, 21:20

... the collocation occurs (both col- location's keys occur on the same sentence, as they are in a syntactical relation). When parallel corpora are available, also the translation equivalents of ... length-based and integrates a shal- low content analysis. It begins by individuating a paragraph in the target text which is a first candi- date as target paragraph, and which we call &...

Ngày tải lên: 22/02/2014, 02:20

... 12CA5 mAb against HA was from Roche (Indianapolis, IN, USA), anti-HA clone HA.11 was from Covance (Berkely, CA, USA), anti-glutathione S-transferase (GST) and mAb against myc (9E10) were from Santa ... 403–410. 29 Altschul SF, Madden TL, Schaffer AA, Zhang J, Zhang Z, Miller W & Lipman DJ (1997) Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Ac...

Ngày tải lên: 07/03/2014, 06:20

... DUC tasks which range from single-/multi-document summa- rization to update summaries, where it is assumed that the reader has already read earlier articles about an event and requires only an ... Hatzivas- siloglou et al. (2001) created a set of 10.535 man- ually marked pairs of paragraphs. Two human an- notator were asked to judge if the paragraphs con- tained ’common information’. They w...

Ngày tải lên: 08/03/2014, 01:20

... consisting of a class label, a selecting head, a grammatical relation, and a filler head. The class label is treated as hidden data in the EM- framework for statistical estimation. 2 EM-Based Clustering ... clustering approach, classes are derived directly from distributional data a sample of pairs of verbs and nouns, gathered by pars- ing an unannotated corpus and extractin...

Ngày tải lên: 08/03/2014, 06:20

... and purification of recombinant FH8, with the use of conventional affinity tags, was not appropriate. As an alternative, a construct was prepared with the H. Fraga et al. FH8 from Fasciola hepatica FEBS ... Silva E, Castro A, Lopes A, Rodrigues A, Dias C, Conceic¸ a ˜ o A, Alonso J, Costa JMC, Bastos M, Parra F et al. (2004) A recombinant antigen recognized by Fasciola hepatica-in...

Ngày tải lên: 15/03/2014, 00:20

... statistical machine translation ( SMT) community as a way of formalizing syntax-based translation models between natural languages (NL). In generating multiple parse trees in a single deriva- tion, ... parsing is cast as a machine translation task, where an SCFG is used to model the translation of an NL into a formal meaning-representation lan- guage (MRL). Our algorithm, WASP, uses s...

Ngày tải lên: 17/03/2014, 04:20