Báo cáo khoa học: "A Web-based Evaluation Framework for Spatial Instruction-Giving Systems" docx

... of the lexical infor- mation without considering other sources of in- formation cues like discourse features, acoustic features, and so forth. 3 A risk minimization framework for extractive ... (manual) transcripts for the summarization performance evaluation (i.e., for the SD case). Observing Table 3 we notice two particulari- ties. First, there are significant performance ga...

Ngày tải lên: 16/03/2014, 23:20

... tentially provide a uniform formalization, allowing disparate theories to be compared on the basis of those properties. We dis- cuss L2,p, a monadic second-order logical framework for such an approach ... characterized as constrain~ based the formalism (or formal framework) provides a class of structures and a means of precisely stating constraints on their form, the linguistic...

Ngày tải lên: 17/03/2014, 09:20

... different in the evaluation methodology for the candidate templates. While the performance of the MUC4 domain is measured for each slot indi- vidually; the MUC6 task measures the perform- ance on ... dependency rela- tions in a multi-resolution framework for IE. The 592 framework enables us to connect entities in differ- ent clauses and thus improve the performance on long-dis...

Ngày tải lên: 23/03/2014, 18:20

... Association for Computational Linguistics:shortpapers, pages 558–563, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics A Probabilistic Modeling Framework for Lexical ... (e.g. parsing) aiming at high performance. Nevertheless, simple entailment methods, per- forming at the lexical level, provide strong baselines which most systems did not outperfor...

Ngày tải lên: 30/03/2014, 21:20

... metric-based framework for the task of automatic taxonomy induction. The framework incrementally clus- ters terms based on ontology metric, a score indicating semantic distance; and transforms the ... of a tax- onomy. For a taxonomy T(C,R), we define its information function as: ∑ ∈< = C y c x cyx yx ccdTInfo ,, ),()( (1) Similarly, we define the information function for a...

Ngày tải lên: 30/03/2014, 23:20

... between 0 and g, for approximately half of the points (those laying in the B region), while the distance is be- tween 0 and h for the other half of the points (those in A). Therefore, if m is large ... whole corpus (BNC). C is the total number of categories. W stands for Written, S for Spoken. C1, C2, DE, UN are demographic classes for the spontaneous conversations, no cat is the BN...

Ngày tải lên: 17/03/2014, 22:20

... by calculating, for each pronunciation form, the fraction of words that are correctly hypothesized and averaging over the test set. For example if the classifier returns five words for a given pronunciation, ... form Q(z i ) ∝          f ins (t b i ) for z (s) i = ; z (t) i = t b i f del (s a i ) for z (s) i = s a i ; z (t) i =  f sub (s a i , t b i ) for (z (s) i , z (t)...

Ngày tải lên: 23/03/2014, 19:20

... complexity, for tests (2) and (3). This indicator is exact for the case of test (2), since the formally marked word is derived from the unmarked one through the addition of an affix (which for adjectives ... linguistic levels. For example, a markedness contrast can arise at the morphology level, when one of the two words is derived from the other and therefore contains an expl...

Ngày tải lên: 31/03/2014, 06:20

... target for prey capture. However, the genetic information for ÔunderdevelopedÕ a-conotoxins targeting other nAChR subtypes might still be present in the snails and could supply novel ligands for ... indicating that at least two other subunits are required for effective channel formation. In Correspondence to A. Nicke, Max Planck-Institute for Brain Research, Deutschordenstr. 46, D-6...

Ngày tải lên: 19/02/2014, 12:20

... paper, we formulate ex- tractive summarization as a two step learn- ing problem building a generative model for pattern discovery and a regression model for inference. We calculate scores for sentences ... 2010. c 2010 Association for Computational Linguistics A Hybrid Hierarchical Model for Multi-Document Summarization Asli Celikyilmaz Computer Science Department University of Cal...

Ngày tải lên: 20/02/2014, 04:20