Báo cáo khoa học: "Combining Clues for Word Alignment" pdf

... combination of clues. Word align- ment clues indicate associations be- tween words and phrases. They can be based on features such as frequency, part-of-speech, phrase type, and the ac- tual wordform strings. ... Using the addition rule for probabilities we get the following formula for a disjunction of two clues: P(ai U a2) = P(ai) P(a2) — P(al n a2) For simplicity, we assu...

Ngày tải lên: 08/03/2014, 21:20

... mechanism to aug- ment one source word into several source words or delete a source word, while a NULL insertion is a mechanism of generating several words from blank words. Fertility uses a conditional ... score S W B,X for each pair of sentences where X is 4, 3, 2, and 1 for word- based MT decoder. Step 3: Train phrase-based MT for full parallel corpus. Note that we do not need to...

Ngày tải lên: 08/03/2014, 01:20

... worse to align two English words at different ends of the tree to the same foreign word, than it is to align two English words under the same NP to the same foreign word. To see why a string distance ... Log- linear Models for Word Alignment In Proceedings of the 43rd Annual Meeting of the ACL. Ann Arbor, Michigan. USA. Robert C. Moore. 2005. A Discriminative Framework for Word Alig...

Ngày tải lên: 23/03/2014, 16:20

... association with respect to a word in a sentence pair to be the number of association types (word- type to word- type) for that word that have higher association scores, such that words of both types occur ... fea- ture sums, for each word w, the number of words not linked to w that fall between the first and last words linked to w. The other features counts only such words that ar...

Ngày tải lên: 08/03/2014, 02:21

... word PROCEDURE: STEP 1. Form a similarity list ]or each sense of one of the words. Pick one of the words, say W2, and using WordNet, form a similarity list for each sense of that word. For ... senses pro- vided in WordNet. The senses are ranked us- ing two sources of information: (1) the Inter- net for gathering statistics for word- word co- occurrences and (2)WordNet fo...

Ngày tải lên: 08/03/2014, 06:20

... domain to improve word alignments for general words and the corpus in the specific domain for domain-specific words. In other words, we will adapt the word alignment information in the general ... target words for the English word i, we add this link into . WA d) Otherwise, if there are two different links for this word: one target is a single word, and the other targe...

Ngày tải lên: 17/03/2014, 06:20

... de- tailed information may not be available, for in- stance for languages for which such a resource does not exist or for expressions that are not very well covered in WordNet, such as idioms. For those ... Meeting of the Association for Computational Linguistics, pages 1138–1147, Uppsala, Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics Topic Models f...

Ngày tải lên: 23/03/2014, 16:20

... of the text in which the word is located is a crucial information for WSD. For example the (domain) polysemy among the COM- PUTER SCIENCE and the MEDICINE senses of the word virus can be solved ... This methodology is called word expert approach (Small, 1980; Yarowsky and Florian, 2002). However this is clearly unfeasible for all-words WSD tasks, in which all the words of an open...

Ngày tải lên: 23/03/2014, 19:20

... on WordNet) in order to perform unsupervised Word Sense Disam- biguation. Our algorithm uses the full graph of the LKB efficiently, performing better than previous approaches in English all-words ... Ppr w2w), where we build the graph for each target word in the context: for each target word W i , we concentrate the initial proba- bility mass in the senses of the words surrounding W...

Ngày tải lên: 31/03/2014, 20:20

... kernel for phrase grammar parse trees and for depen- dency parse trees outperforms all known tree kernel approaches alone suggesting that both types of trees contain comple- mentary information for ... dependency parse tree kernel outperforms all others by 5.7% F-Measure reaching an F-Measure of 71.2%. This result shows that both types of parse trees contain relevant information for r...

Ngày tải lên: 20/02/2014, 09:20