Báo cáo khoa học: "Head-Driven Generation with HPSG" pdf

... infrastructure to sup- port the creation of, experimentation with, and evaluation of coreference resolvers. Reconcile was designed with the following seven desiderata in mind: • implement the ... present). The basic architecture of the system includes five major steps. Starting with a corpus of docu- ments together with a manually annotated corefer- ence resolution answer key 1 , Reconc...

Ngày tải lên: 20/02/2014, 04:20

... Recall. In fact if tn is large with respect to both rp and pp, and thus with respect to components tp, fp and fn, then both tn/pn and tn/rn approach 0 as tn increases without bound. As discussed ... is in fact a variant of Kappa with some similarities to Cohen Kappa, but also some advantages over both Cohen and Fleiss Kappa due to its asymmetric relation with Recall, in the di...

Ngày tải lên: 22/02/2014, 02:20

... PR with the V32I mutation; PR I50V , PR with the I50V mutation; PR I54M , PR with the I54M mutation; PR I54V , PR with the I54V mutation; PR I84V , PR with the I84V mutation; PR L90M , PR with ... compared with PR WT –SQV. (B) PR I50V –APV compared with PR I50V –SQV. (C) PR I54M –APV compared with PR I54M –SQV. (D) PR I54V –APV compared with PR I54V –SQV. (E) PR I84V –APV...

Ngày tải lên: 18/02/2014, 04:20

... site. Generation of null mutants in those genes by homologous recombination mutagenesis and protein purification allowed us to correlate each gene with its enzymatic activity. In contrast with ... R3. The PCR product with a size of  1.6 kb was digested with BamHI to obtain a fragment between the two copper-binding site coding regions and ligated to pBlueScript pKSII(+) with T4 DNA...

Ngày tải lên: 19/02/2014, 07:20

... a pattern with which to expand it and then filling out that pattern with words drawn from a unigram distribution. This kind of coupled generative process can be naturally formalized with tree ... gen- erate MR and NL associated with MR rules m -v (top). Transducer rule 2 selects MR rule r from the MR gram- mar. Rule 3 simultaneously writes the MR associated with rule m and chooses an...

Ngày tải lên: 19/02/2014, 19:20

... the SRH. We show the performance of GIZA++ and HM- BiTAM with the SRH in the lines entitled with SRH” in Table 1. The GIZA++ and HM-BiTAM with the SRH slightly outperformed the standard GIZA++ ... alignment model. We formulate a syn- onym pair generative model with a topic variable and use this model as a regularization term with a bilingual word alignment model. The topic vari- able...

Ngày tải lên: 20/02/2014, 04:20

Ngày tải lên: 20/02/2014, 04:20

... of solving discourse generation problems using stochastic models. Our generation algorithms are fundamentally differ- ent from previously-proposed algorithms for dis- course generation. The genetic ... algorithms of Section 3, implement- ing A search, histogram beam search with a beam of 100, and histogram beam search with a beam of 1, respectively. We compare our algo- rithms agains...

Ngày tải lên: 20/02/2014, 12:20

... node in an elementary tree, except for ones with null ad- junction constraints, is marked with a semantic role, and that all substitution nodes are marked with dif- ferent roles. Nothing hinges on ... goals. In this paper, we make this perspective explicit by translating the sentence generation problem of TAG grammars with semantic and pragmatic information into a planning problem s...

Ngày tải lên: 20/02/2014, 12:20

... using a custom-built unit-selection voice with support for APML prosodic annotation (de Carolis et al., 2004). Experiments have shown that synthesised speech with contextually appropriate prosodic ... Introduction COMIC 1 is an EU IST 5th Framework project com- bining fundamental research on human-human inter- action with advanced technology development for multimodal conversational sys...

Ngày tải lên: 20/02/2014, 15:20