báo cáo khoa học: "Jeannine BOSCHER in a hypoprolific boar" pptx

... of a natural language system is that it often has only partial information about the individuals (objects, events, and relations) that are talked about. Unless one assumes that the original ... predicate ROLE and making rolenames into individuals in the domain. ROLE(o, r, v) asserts that individual o has a role named r that is filled with individual v. To distinguish rolenames...

Ngày tải lên: 21/02/2014, 20:20

... Introduction In this paper we investigate how features of a text discovered via automatic event extraction can be used in both natural language understanding and advice generation in the domain of narrative ... Wiemer- Hastings, 2002). As shown by participatory de- sign studies, teachers are interested in a plot anal- ysis agent that can give online natural language advice and man...

Ngày tải lên: 20/02/2014, 12:20

... containing parallel items, and abstracts over these items in both representations. If the resulting representations are unifiable, the two sen- tences stand in a contrast relation and the parallel ... Another advantage, pointed out in (Gardent et al., 1996), is that a HOU algorithm can take world know- ledge into account, which is sometimes necessary for determining contrast....

Ngày tải lên: 22/02/2014, 03:20

... in a compact way. We also compile each grammar rule into a finite state automaton. Each rule automaton can be regarded as a constraint that accepts some readings and rejects some. For example, ... Helsinki, 1991. [Tapanainen, 1992] Past Tapanainen. Jk/irellisiin automaatteihin perustuva luonnollisen kielen j/isennin (A finite state parser of natural lan- guage). Licentiate (p...

Ngày tải lên: 22/02/2014, 10:20

... Jorge Hankamer and Ivan Sag. Deep and surface anaphora. Linguis- tic Inquiry, 7(3):391-428, 1976. [Johnson and Klein, 1986] Mark Johnson and Ewan Klein. Discourse, Anaphora, and Parsing. In Coi- ... Nancy gives a man an iron. Nancy likes a man who has an iron that (9) a woman gave him. 3 Negation Concerning predicate negation, we will assume that the scope of negation does no...

Ngày tải lên: 22/02/2014, 10:20

... English and a French versions of a software manual contain 628 and 640 paragraphs, respectively. In all, there are 30 para- graphs embedded in them which do not have a trans- lation (some in fact ... Grove, CA., 1991. Morgan Kaufmann. [Gale and Church, 1991b] William A. Gale and Kenneth W. Church. A program for alinging sen- tences in bilingual corpora. In Proceedin...

Ngày tải lên: 22/02/2014, 10:20

... artifi- cial covalent flavinylation (again, FAD is linked via an 8-carbon rather than 8a- carbon linkage) resulted in an increased k cat value with d-alanine from 1.5 s )1 for the mutant enzyme, containing ... of covalent flavin–protein linkages. FMN is show in black, FAD in black and gray, and known linking amino acids in green. Sites of covalent attachment are indicated by arrows. The...

Ngày tải lên: 16/03/2014, 01:20

... 23977–23990. 22 Nakayama M, Suzuki H, Yamamoto-Nagamatsu N, Barman HK, Kikuchi H, Takami Y, Toyonaga K, Yamashita K & Nakayama T (2007) HDAC2 controls IgM H- and L-chain gene expressions via EBF1, Pax5, Ikaros, ... 2, 195–199. 31 Matsushita N, Takami Y, Kimura M, Tachiiri S, Ishiai M, Nakayama T & Takata M (2005) Role of NAD- dependent deacetylases SIRT1 and SIRT2 in radiation and c...

Ngày tải lên: 16/03/2014, 04:20

... can be naturally extended to other platforms since only the avatar interfaces have to be adapted. The integration architecture also has the advan- tage that the necessary services can be easily ... dialog manager takes the result of the input analyzer and delivers an interpretation based on the dialog context and the available knowledge. It also controls the task conversation chain and han- d...

Ngày tải lên: 17/03/2014, 00:20

... segmentation. Machine Learning, 34(1-3):177 – 210. Brill, Eric. 1995. Transformation-based error-driven learning and natural language processing: A case study in part-of-speech tagging. Computational Linguistics, ... probabilities are estimated by standard language modeling techniques. We cre- ate speaker-specific models by linearly interpolating an m-gram model based on data from the user...

Ngày tải lên: 17/03/2014, 02:20