Báo cáo khoa học: "A FRIENDLY AND FLEXIBLE FRONT-END FOR DATA MANAGEMENT SYSTEMS" pptx

... EUFID: A FRIENDLY AND FLEXIBLE FRONT-END FOR DATA MANAGEMENT SYSTEMS Marjorie Templeton System Development Corporation, Santa Monica, CA. EUFID is a natural language frontend for data management ... enough for him. For example, for efficiency a user might prefer to use "wh" for "warehouse" and "co" for "company". An...

Ngày tải lên: 08/03/2014, 18:20

... algorithm. 4.1 Data Structures We exploit two data structures for candidate genera- tion. One is a trie for storing and matching words in the vocabulary, referred to as vocabulary trie, and the other ... final candidate selection, e.g., Li et al. (2006), Golding and Roth (1999). In spelling error correction, Brill and Moore (2000) proposed employing a generative model for can...

Ngày tải lên: 30/03/2014, 21:20

... NP”, and “VP→ADVP VP” are used as features for s 1 , s 2 and s respectively. • Path Features (PF) The tree path σ(s 1 ) σ(s) connecting σ(s 1 ) and σ(s), σ(s 2 ) σ(s) connecting σ(s 2 ) and σ(s), ... (2005) introduces a count for each hypothesis and ac- cumulates it whenever the hypothesis exactly matches syntactic boundaries on the source side. On the contrary, Marton and Res...

Ngày tải lên: 20/02/2014, 07:20

... meth- ods can perform better. In order to make full use of the syntactic information and the standard flat features, we present a composite kernel between hybrid kernel (K hybrid ) and standard features ... kernels, more and more kernels for restricted syntaxes or specific do- mains, such as string kernel for text categoriza- tion (Lodhi et al., 2002), tree kernel for syntactic pars...

Ngày tải lên: 20/02/2014, 12:20

... standing for X spanning f j i . We choose b and β to balance speed and performance on our development set. For our experiments, we set b = 40, β = 10 −1 for X cells, and b = 15, β = 10 −1 for ... al. of designating the source and target languages as “French” and “English,” respectively. The variables f and e stand for source and target sentences; f j i stands for the...

Ngày tải lên: 17/03/2014, 05:20

... ACQUISITION Recently, several researchers, including Gibson and Wexler (1994), henceforth GW, Dresher and Kaye (1990); and Clark and Roberts (1993) have modeled language learning in a (finite) ... phrase, and so forth. Given these alternatives, Gibson and Wexler (1994) show that there are 12 possible surface strings for each (-V2) grammar and 18 possible surface strings...

Ngày tải lên: 23/03/2014, 20:21

... PST as a knowl- edge source for DA detection, we essentially need to model the relationship between the random DA and the random DR. Denote the random DA by X and the random DR by Y . Given a text ... SDS. Figure 1 depicts the training and test phases of the SLU module and the DM module in our system. The data ow for training and testing are indicated by blue arrows and red a...

Ngày tải lên: 20/02/2014, 05:20

... be learned and saves more potential exam- ples of fluent speech rules, and therefore potentially makes better use of limited data. 3 Evaluation The evaluation of this system was performed on the ... using the mrg annotations in directories 2 and 3 for training, and the files sw4004.mrg to sw4153.mrg in directory 4 for evalu- ation, following Johnson and Charniak(2004). The input...

Ngày tải lên: 20/02/2014, 09:20

... () bw tf w idf b idf b ⊂ ⋅ ∑ in which b 1 and b 2 stand for the two bigrams and w stands for any word containing both of them. The overall information quantity is obtained by subtracting ... fluctuations for the same reason. For a parallel comparison among mmword, lqword and bigram schemes, the curves in Fig- ure 1 and Figure 2 are regrouped and shown in Figure 3 a...

Ngày tải lên: 08/03/2014, 02:21

... $Cognitive and Computing Sciences, University of Sussex Falmer, Brighton BN1 9QH, UK *Center for the Study of Language and Information, Stanford University Ventura Hall, Stanford, CA 94305-4115, ... a sophisticated typed feature formalism (Krieger and Sch~ifer, 1994; Krieger and Sch~ifer, 1995) and an advanced agenda-based bottom-up chart parser (Kiefer and Scherf, 1996)....

Ngày tải lên: 08/03/2014, 06:20