Báo cáo khoa học: "Typed Graph Models for Semi-Supervised Learning of Name Ethnicity" pptx

... part of the First name/ Last name graph: Edges indicate co-occurrence or a shared name. Character Ngram graph The ethnicity of personal names are often indi- cated by morphophonemic features of ... experimented with three kinds of graphs for this task: First name/ Last name (FN LN) graph As a first attempt, we only considered first and last names as features generated by...

Ngày tải lên: 30/03/2014, 21:20

... type of phrase contains most of interesting properties of phrases, such as emergence or inversion of se- mantic orientations. In order to capture the properties of semantic orientations of phrases, ... difference of the values of Q-function before and after an iteration becomes smaller than a threshold, we regard it as converged. For classification of an unknown pair n, a,...

Ngày tải lên: 17/03/2014, 22:20

... Interface information could be obtained for example for the complex of HscA with IscU LPPVK motif-containing peptides [127]: the ability of Trp residues at the N-terminus or C-terminus of the peptides ... presence of increasing amounts of the partner protein (‘titration experiments’). Changes in chemical shifts of one molecule on addition of a sec- ond molecule allow assessm...

Ngày tải lên: 30/03/2014, 15:20

... candidates. 2.3 Learning the Model For learning of the model, we borrow a funda- mental idea of Kazama and Torisawa’s perceptron learning algorithm. However, we use a more so- phisticated online -learning ... number of N-bests was set to N = 64. For learning of the joint model, the loss function ρ(y t , y  ) of the Passive-Aggressive Algorithm was set to the number of...

Ngày tải lên: 30/03/2014, 21:20

... increase the number of unlabeled data, with our graph- summarization, it is feasible to extract information that can improve the performance of QA models. We performed experiments on a set of 1449 questions ... effect of number of unlabeled data on MRR from Hybrid graph Summarization SSL. of the models. As more labeled data is introduced, Hybrid SVM models performance incr...

Ngày tải lên: 20/02/2014, 07:20

... These types of infor- mation provide rich clues for building dialog mod- els (Grosz and Sidner, 1986). Dialog models can be built of ine (for dialog mining and summariza- tion), or online (for dialog ... history Nbest F start!complete connection!paths shift!reduce Figure 5: Performance of parse-based methods for subtask tree building Figure 5 shows the performance of the differ...

Ngày tải lên: 22/02/2014, 02:20

... perform preprocess- ing (refer to Section 3.4 for details) before build- ing topic models for C R (q), where some low- frequency items are removed. Determine the number of topics: Most topic models ... the above formula, nDCG(G i,j ) is the nDCG score of semantic class G i,j ; and k i denotes the number of semantic classes assigned to SSC i . For a list of queries, the...

Ngày tải lên: 08/03/2014, 00:20

... Proceedings of the 12th Conference of the European Chapter of the ACL, pages 202–210, Athens, Greece, 30 March – 3 April 2009. c 2009 Association for Computational Linguistics Re-Ranking Models For ... SRILM tools and then converted to an FST. This allows the use of a wide set of stochastic language models (both back-off and interpolated models with several dis- counting...

Ngày tải lên: 08/03/2014, 21:20

... can be formed out of smaller rules (includ- ing larger phrase pairs that can be formerd out of smaller phrase pairs), as opposed to minimal rules, which are rules that cannot be formed out of other rules. ... results of our paper. We used grammars of minimal rules and composed rules of maximum height 3 as our baselines. For decod- ing, we used a beam size of 50. Using the best...

Ngày tải lên: 17/03/2014, 00:20

... model of the possible alignments in the form of flow net- works. This representation allows to define dif- ferent kinds of alignments and to find the most probable or an approximation of this ... notion of flow networks that we can formalise in the following way (we as- sume that the reader has basic notions of graph theory). Definition 1: let G = (17, E) be a directed...

Ngày tải lên: 17/03/2014, 07:20