Báo cáo khoa học: "Better Word Alignments with Supervised ITG Models" pdf

... show that our ITG alignments yield improve- ments in translation quality. thresholding (DeNero and Klein, 2007). The ITG Viterbi alignments are the Viterbi output of the ITG model with all features, ... normal cell if it was constructed with a normal rule and inverted if constructed with an inverted rule. Each ITG derivation yields some alignment. The set of such ITG alig...

Ngày tải lên: 17/03/2014, 01:20

... many-to-one word alignments, where each source word is aligned with zero or one target words, and therefore each target word can be aligned with many source words. Each source word is labelled with ... one-to-many alignments, where each target word is aligned with zero or more source words. Many-to-many alignments are recoverable using the standard techniques for superi...

Ngày tải lên: 20/02/2014, 11:21

... the interpretation of word senses. Different interpretations of word senses result in different so- lutions to word sense learning. One interpretation strategy is totreat a word sense as a set ... discovered tight clusters called committees by grouping top n words similar with target word using average- link clustering. Then the target word was assigned to committees if the simi...

Ngày tải lên: 20/02/2014, 16:20

... data has been annotated with both sure alignments S and possible alignments P , with S ⊆ P , ac- cording to the specifications described in Och and Ney (2003). With these alignments, we compute ... VBN NNS DT AUX The jobs are career oriented . les emplois sont axés sur la carrière . . Legend Correct proposed word alignment consistent with human annotation. Proposed word align...

Ngày tải lên: 08/03/2014, 02:21

... of NAACL, New York. A. Haghighi, J. Blitzer, J. DeNero, and D. Klein. 2009. Better word alignments with supervised ITG models. In Proc. of ACL-IJCNLP. P. Koehn, F. J. Och, and D. Marcu. 2003. Statistical phrase-based ... NeurAlign: combining word alignments using neural networks. In Proc. of HLT-EMNLP. T. Berg-Kirkpatrick, A. Bouchard-C ˆ ot ´ e, J. DeNero, and D. Klein. 2010. P...

Ngày tải lên: 17/03/2014, 00:20

... initial word set {B, C}. First, we find the tuple with the greatest CSM value among the tuples in which the word C at the tail of the current word set is the left word, and connect the right word ... Next, we find the tuple with the greatest CSM value among the tuples in which the word B at the head of the current word set is the right word, and connect the left word...

Ngày tải lên: 17/03/2014, 04:20

... problems may occur when estimating either P(T|L) with unknown word w i or P(L) with unknown events. Bikel et al. (1999) mapped all unknown words to one token _UNK_ and then used a held-out ... probability calculated with Formula 9 and x=E i /S i (E i is the number of words appearing only once in state i and S i is the total number of words occurring in state i). For unknow...

Ngày tải lên: 20/02/2014, 15:20

... tablet', either with or without coreference, and paste it onto the anchor something, obtaining two possible outcomes: Remove a tablet from the foil and swallow it [with coreference] Remove ... created with WYSIWYM was converted into a logical formula for submis- sion to the inference engine; it was web-delivered — the user interface was written as a JAVA applet communicating w...

Ngày tải lên: 17/03/2014, 22:20

... the WordNet 1.7 inventory. After pruning stopwords, we end up with 16,186 English words, 31,862 Span- ish words and 2,385,574 instances of 41,850 distinct translation pairs. The English words ... has other words like bar that occur in the corpus and all of these other words are observed to be translated in Spanish as the word obstrucci ´ on. In addition, none of these other words translat...

Ngày tải lên: 08/03/2014, 04:22

... North American Business News (NAB) corpus contains 250 million words, with a vocabulary of 463,331 words. The Switchboard training corpus has 3.1 million words, and a vocabulary of 45,643. The number of transitions ... exact online representation with failure transitions. We will call an -transition within a path in- valid if the next non- transition , , has the la- bel , and there is a t...

Ngày tải lên: 08/03/2014, 04:22