Báo cáo khoa học: "A Comparison of Syntactically Motivated Word Alignment Spaces" doc

... A Comparison of Syntactically Motivated Word Alignment Spaces Colin Cherry Department of Computing Science University of Alberta Edmonton, A B, Canada, T6G ... in- dividual word- to -word connections that make up an alignment. An alignment space determines the set of all possible alignments that can ex- 145 ist for a given sentence pair. Alignment spaces can ... restr...

Ngày tải lên: 08/03/2014, 21:20

... em- ploying each of these parsing alternatives? Each of these four questions is addressed in the four subsequent sections of this paper, fol- lowed by a discussion of the implications of our findings ... structures as a set of de- pendency relationships between words, typed asymmetric binary relationships between head words and modifying words. Figure 2 depicts the output o...

Ngày tải lên: 20/02/2014, 12:20

... The principle of bottom-up parsing is to reduce a sequence of phrases whose types match the right- hand side of a grammar rule to a phrase of the type of the left-hand side of the rule. To ... processing of different grammatical formalisms. At the same time it is of course a natural test bed for experiments with various control strategies. Previously a number of compa...

Ngày tải lên: 09/03/2014, 01:20

... full-text of a document. We com- pared the abstract and non-abstract terms in each of the three language models. Not all of the documents distinguished the ab- stract from the body. Of the 100,830 documents, ... This comparison reflects a previous analysis comprising a random sample of 193 words from a 50 million word corpus of 85,432 news articles (Church and Gale 1999)....

Ngày tải lên: 17/03/2014, 04:20

... Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, pages 11–16, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics A Comparison ... generalizations of words — are another feature known to be useful for dependency parsing. Here we lemmatized each Chinese word down to its last character, since — in contras...

Ngày tải lên: 23/03/2014, 14:20

... Proceedings of ACL- 08: HLT. W. Jiang, L. Huang, Q. Liu, and Y. L ¨ u. 2008. A cas- caded linear model for joint Chinese word segmen- tation and part -of- speech tagging. In Proceedings of ACL-08: ... Computational Linguistics A Comparison of Loopy Belief Propagation and Dual Decomposition for Integrated CCG Supertagging and Parsing Michael Auli School of Informatics University o...

Ngày tải lên: 23/03/2014, 16:20

... number of words in the source which are judged to have been mistranslated. For the purposes of this definition, mistranslation of a source word includes choice of the wrong target word (or words), ... Selection of a pair of words wo E V1 and vo E V2, and a head transducer 3,10 to start the entire derivation. Selection of a pair of dependent words w I and v ~ and t...

Ngày tải lên: 24/03/2014, 03:21

... captures the information of which words are used in a document, but not the number of times each words is used, nor the order of the words in the document. In the second model, a document is generated by ... new document, the classifier outputs the class which is most likely to have generated the document. From a linguistic point of view, a document is made up of words, and the sema...

Ngày tải lên: 31/03/2014, 20:20

... the form of a non-finite complement 3 For lack of space, here we cannot go into aspects of word- order variation (both Estonian and German are languages with relatively free word order). ... identity, where only the word- stems of the constitu- ents have to be identical, and wordform identity, which re- quires not only identity of the stems but also of their mor- pholo...

Ngày tải lên: 31/03/2014, 20:20

... Improve Word Alignment Colin Cherry and Dekang Lin Department of Computing Science University of Alberta Edmonton, Alberta, Canada, T6G 2E8 {colinc,lindek}@cs.ualberta.ca Abstract Word alignment ... directly, using a different decomposition of terms. In the IBM models of translation, alignments exist as artifacts of which English words generated which French words. Our model...

Ngày tải lên: 17/03/2014, 06:20