Báo cáo khoa học: " Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques" doc

... Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques Stefan Riezler Tracy H. King Ronald M. Kaplan Palo Alto Research Center Palo Alto ... sys- tem to parsing the UPenn Wall Street Journal (WSJ) treebank. The model com- bines full and partial parsing techniques to reach full grammar coverage on un...

Ngày tải lên: 23/03/2014, 20:20

... Reducing the Grammar Size and Smoothing Issues As grammars are being inferred at each iteration, the training algorithm was designed to guarantee that no parameter was set below some small threshold. ... grammars (SCFG) which can be used for grammar reestimation (Fujisaki et al. 1989, Sharrnan et al. 1990, Black et al. 1992, Briscoe and Wae- gner 1992) or grammar inferenc...

Ngày tải lên: 01/04/2014, 00:20

... of many words. Though it has been the standard practice for many years, we argue that this paradigm is inadequate both in theory and in practice, for at least the following four reasons. The ... p) (9) The other probabilities can be estimated in the same way. 4.4 Summary of the Generative Story We make a brief summary of our generative story for the integrated morphological...

Ngày tải lên: 17/03/2014, 00:20

... Efficient Estimation The L-BFGS algorithm requires the following val- ues at each iteration: the expected value, and the empirical expected value, of each feature (to calcu- late the gradient); and the ... Hockenmaier effectively reads a lexicalised PCFG off CCGbank, and is able to use all of the available training data; Hockenmaier does not use a supertagger, but doe...

Ngày tải lên: 23/03/2014, 19:20

... takes a set of categories {a~ , a~ , } as input. It outputs a particular category a~ z such 243 that the product of the probability that A: is the category a~ , and the probability that the category ... substan- tially reduces the time and space the parser needs for a given parse, and increases the parser's accuracy. The parser introduces syntacti...

Ngày tải lên: 31/03/2014, 18:20

... pET A3 A 4A5 – atdA2 pACYC A1 and pET A3 A 4A5 + atdA3 pACYC A1 A2 and pET A4 A5 – Control (no deletion) pACYC A1 A2 and pET A3 A 4A5 + E. L. Ang et al. Substrate specificity of aniline dioxygenase FEBS Journal ... the A2 _FseI_F and A2 _AvrII_R primers. The atdA3 gene was amplified using the A3 _EcoRI_F and A3 _SalI_R primers. The atdA 4A5 gene was amplified us...

Ngày tải lên: 19/02/2014, 02:20

... of data as depicted in Figure 1. In contrast, we are interested in applying AL when a large amount of data already exists as is the case for many important lanuage pairs. We de- velop an AL algorithm ... small set of seed data. Also, by SMT stan- dards, they only add a very tiny amount of data during AL. All their simulations top out at 10,000 sentences of labeled data and the model...

Ngày tải lên: 20/02/2014, 04:20

... edge-ordered and labeled. A solution for a dominance constraint con- sists of a tree τ and a variable assignment α that maps variables to nodes of τ such that all constraints are satisfied: a labeling ... Saarlandes niehren@ps.uni-sb.de Stefan Thater Computational Linguistics Universit¨at des Saarlandes stth@coli.uni-sb.de Abstract Minimal Recursion Semantics (MRS) is the stand...

Ngày tải lên: 20/02/2014, 16:20

... and s( f 2j )( j ¼ 1, 2, 3) are variant in the FNS (Supplementary material, Supplementary mathematical descriptions, Theorem 5). On the other hand, we note that the signs of f 31 , f 42 are all ... Supplementary material, Supplementary mathematical descriptions) and in this case we simply say that the experimental data set is a fully excited information set at x i . For instance...

Ngày tải lên: 07/03/2014, 21:20

... specificity measuring. A set of journal abstracts was extracted from MEDLINE 2 database using the disease names as quires. Therefore, all the abstracts are related to some of the disease names. The ... the term is calculated incrementally starting from head noun. In this manner, specificity value of a term is always lar- ger than that of the base (head) term. This re...

Ngày tải lên: 08/03/2014, 04:22