Báo cáo khoa học: "Optimizing Grammars for Minimum Dependency Length" pptx

... 184–191, Prague, Czech Republic, June 2007. c 2007 Association for Computational Linguistics Optimizing Grammars for Minimum Dependency Length Daniel Gildea Computer Science Dept. University ... word order for a set of dependency trees so as to minimize total dependency length. We present an algorithm for computing the op- timal layout of a single tree as well as a numerica...

Ngày tải lên: 23/03/2014, 18:20

... Association for Computational Linguistics, pages 629–637, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Selective Sharing for Multilingual Dependency ... features. When performing unsupervised learning for the target language, we need to marginalize over possi- ble derivations. Specifically, for the M step, we need probabilities of the f...

Ngày tải lên: 16/03/2014, 19:20

... interface for Information Retrieval. Proceedings of the 6th Annual International ACM SIGIR Conference, ACM Special Interest Group on Information Retrieval and American Society for Infor- mation ... word gets transmitted and no pattern for it exists in a base IRule for the head word, higher IRules are searched for the pattern. If a pattern does exist for the modifier in a gi...

Ngày tải lên: 08/03/2014, 18:20

... to minimize some information loss such as the KL divergence KL(p  q). The simpler model q can then act as a surrogate for p during inference. 3.2 Variational Decoding for MT For each input sentence ... q ∗ (· | h) constrained to be a normalized distribution for each h. 596 Brute-Force-MLE(HG(x )) 1 for y, d in HG(x) ✄ each derivation 2 for w in y ✄ each n-gram type 3 ✄ accumulate...

Ngày tải lên: 23/03/2014, 16:21

... appointment scheduling domain is there- fore ideal for a case study aimed at extracting linguistic indicators for definiteness. 3.1 Overview Explicit marking for definiteness takes place on several ... target language. For this paper, we propose a rule hierarchy for this purpose, that can be used as a pre- processing tool to context checking. All noun phrases marked for de...

Ngày tải lên: 23/03/2014, 19:20

... for each tar- get relation, an integrated model to weight the dif- ferent extraction options, including for example the likely lengths for events, or the fact that start times should come before ... features. In addition, we enforce label consistency and semantic coherence at record level. Other related works perform structured relation discovery for different settings of information...

Ngày tải lên: 30/03/2014, 17:20

... Tie-Yan Liu, Jun Xu, and Hang Li. 2010. Letor: A benchmark collection for research on learning to rank for information retrieval. Information Retrieval, 13(4):346–374. S. Shalev-Shwartz, Y. Singer, ... both query and document in- formation, a probabilistic weighting for ⟨x i , x j ⟩ was modeled by w q ∗ w ij . Through the transformation, instance weighting schemes for classification ca...

Ngày tải lên: 30/03/2014, 21:20

... Transforming the entire for- est to n-ary form is intractable, however, because the number of hyperedges would be exponential in n. Instead, we include only the top k n-ary back- traces for each forest ... Collapsing Binarization To facilitate a change in binarization, we transform the translation forest into n-ary form. In the n-ary forest, each hyperedge corresponds to an original gramm...

Ngày tải lên: 20/02/2014, 09:20

... after all: • For bilexicalized context-free grammars, O(n 4) is possible. • The O(n 4) result also holds for head au- tomaton grammars. • For a very common special case of these grammars where ... O(n 4) results for the natural formalism of bilexical context-free grammar, and for AI- shawi's (1996) head automaton grammars. For the usual case, split head automaton...

Ngày tải lên: 20/02/2014, 19:20

... that Foreign word f j is aligned with English word e i . The direction of word alignments is ignored. Since the goal of word alignment com- bination is for phrase table training, we first for- mally ... precision. For word alignment combination, we focus on the set with high accuracy where n = 0. Let A 1 , A 2 denote two sets of word alignments to be combined for the given sentence pai...

Ngày tải lên: 17/03/2014, 02:20