Báo cáo khoa học: "Bootstrapping via Graph Propagation" potx

... distributions and graph structures are shown in table 2. Figure 1 shows example graphs for φ-θ and θ-only. π-θ and θ T -only are similar, and are described below. The graph structure of φ-θ is the bipartite graph of ... respectively (Nigam et al., 2000). 4 Graph propagation The graph propagation of Subramanya et al. (2010) is a method for smoothing distributions attached to vertices...

Ngày tải lên: 16/03/2014, 19:20

... different depths of subgraphs as long as the subgraphs of each of them are unified successfully. This way, when a failure is finally de- tected at some deep location in some subgraph, other numerous ... Graph unification is the most expensive part of unification-based grammar parsing systems. For ex- ample, in the three types of parsing systems currently used at ATR ], all of which...

Ngày tải lên: 17/03/2014, 08:20

... Republic, June 2007. c 2007 Association for Computational Linguistics Bootstrapping Word Alignment via Word Packing Yanjun Ma, Nicolas Stroppa, Andy Way School of Computing Dublin City University Glasnevin, ... which can be quite hard for lan- guages such as Chinese for which word boundaries are not orthographically marked. More importantly, however, this segmentation is often performed in...

Ngày tải lên: 31/03/2014, 01:20

... combined in a unified graph- based model, which can effectively rank the docu- ments. Compared with existing approaches, experimental results on the COAE08 dataset showed that our graph- based model ... term). Furthermore, based on word pairs, we designed a unified graph- based method for opinion retrieval (see later in Section 3). 3 Graph- based model 3.1 Basic Idea Different f...

Ngày tải lên: 20/02/2014, 04:20

Ngày tải lên: 20/02/2014, 11:21

... binary rules. Theorem 2 For all F ∈ H 1 , G ∈ H 2 that sat- isfy rule independence and are nontrivial predic- tors in the sense that min u Pr[F = u] > Pr[F = G], one of the following inequalities ... same regardless of the value of Y . In these cases, however, the predictors do not satisfy the “non- triviality” condition of theorem 2, which re- quires that min u Pr[F = u] be greater than...

Ngày tải lên: 20/02/2014, 21:20

... 128–135. A. P. Dempster, N. M. Laird, and D. B. Rubin. 1977. Maximum likelihood from incomplete data via the EM algorithms. Journal of the Royal Statistical So- ciety. Series B (Methodological), 39(1):1–38. P. ... on Paraphrasing (IWP2003), pages 65–71. Benjamin Snyder and Regina Barzilay. 2007. Database-text alignment via structured multilabel classification. In Proceedings of Internation...

Ngày tải lên: 07/03/2014, 22:20

... Graph YAGO Graph TextRunner + YAGO Graph 0.3 0.338 0.375 0.413 0.45 LP-ZGL Adsorption MAD 170 WordNet Classes, 10 Seeds per Class Mean Reciprocal Rank (MRR) Algorithms TextRunner Graph YAGO Graph TextRunner ... Table 1): TextRunner Graph: Graph constructed from the hypernym tuples extracted by Tex- tRunner, as in Figure 5 (Section 3.3), with 175k vertices and 529k edges. YAGO Gr...

Ngày tải lên: 07/03/2014, 22:20

Ngày tải lên: 07/03/2014, 22:20

... rows and columns of its alignment graph are associated with the words in the sentence. Un- like the alignment graph used in biological se- quence alignment, the graph is triangular because the ... method upon which our improvements are made. 2.1 Triangular alignment graph The basis of their method is a triangular align- ment graph, illustrated in Figure 1(a). Kurohashi and Nagao (199...

Ngày tải lên: 08/03/2014, 01:20