Báo cáo khoa học: "Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections" doc

... Word n-grams Entropy minimization Entropy minimization with clustering Entropy minimization with filtering Entropy minimization with filtering and clustering # 0 936 16271 1053 1029 ... tag. Brill (1995b) developed an unsupervised version of TBL for Part-of-Speech Tagging, but this algo- rithm must be initialized with words that can be tagged unambiguously, 13 and in...

Ngày tải lên: 23/03/2014, 19:20

... Perl. 23 ate He He:1:2-ate:2:0 ate meat ate:1:0-meat:2:1 ate with ate:1:0 -with: 2:1 meat the the:1:2-meat:2:0 with fork with: 1:0-fork:2:1 fork a a:1:2-fork:2:0 Figure 4: Examples of bigram-subtrees ate meat with ate:1:0-meat:2:1 -with: 3:1 ate with ... the parser with the monolingual features monolingual parser. 3.2 Parsing with bilingual features In this paper, we parse sou...

Ngày tải lên: 16/03/2014, 23:20

... jump conjoined with an indicator feature for the target length n, the dis- cretized jump feature conjoined with the class of s a j , and the discretized jump feature conjoined with the class ... California. K. Gimpel and N. A. Smith. 2009. Cube summing, ap- proximate inference with non-local features, and dy- namic programming without semirings. In Proc. of EACL. N. Habash and F. Sada...

Ngày tải lên: 17/03/2014, 00:20

... the “music” sense. Document theme: Sometimes, the same pattern can express different relations in different docu- ments, depending on the document’s theme. For instance, in a document about politics, ... argument are added with prefix “lc:”. Similarly the two words to the right of the destination arguments are added with prefix “rc:”. Each document in the NYT corpus is associated with man...

Ngày tải lên: 23/03/2014, 14:20

... an abundance of bilingual documents and many more can potentially be mined from the web. It should be possible using our approach to (noisily) assign sense tags to words in such documents, thus providing ... approaches to word- sense disambiguation. For example, the use of par- allel corpora for sense tagging can help with word sense disambiguation (Brown et al., 1991; Dagan, 1991; Daga...

Ngày tải lên: 08/03/2014, 04:22

... binary classification simply deals with the is/is-not relationship and will have difficulty when two responses with similar feature values are clas- sified differently. With preference ranking, viola- tions ... appropriate candidates. 4 Experiments To compare with the prior approach of Pinchak and Lin (2006), we use a set of what and which questions with question focus (questions with...

Ngày tải lên: 08/03/2014, 21:20

... sentences. The primary problem with this model is that most of the model features encode properties related to including or dropping constituents from the tree with no encoding of bigram or trigram ... analysis of the sentence. To do this we parse every sentence twice, once with a dependency parser (McDon- ald et al., 2005b) and once with a phrase-structure parser (Charniak, 2000). Th...

Ngày tải lên: 24/03/2014, 03:20

... the value of feature F; as usual in Prolog, symbols starting with a lower-case letter are con- stants, while symbols starting with an upper-case letter are variables. Focus and mention vectors ... problem of updating mention ratios by unification, without resorting to statements like Df is Di + 1. This can be done by replacing numbers with lists of the appropriate length, so that...

Ngày tải lên: 24/03/2014, 03:20

... 19-24, 2011. c 2011 Association for Computational Linguistics Unsupervised Part-of-Speech Tagging with Bilingual Graph-Based Projections Dipanjan Das ∗ Carnegie Mellon University Pittsburgh, ... Ryan McDonald. 2011. A universal part-of-speech tagset. ArXiv:1104.2086. Sujith Ravi and Kevin Knight. 2009. Minimized models for unsupervised part-of-speech tagging. In Proc. of ACL-I...

Ngày tải lên: 30/03/2014, 21:20

... expected semantic role se- quence. Sentence a is in active voice with sequence (A0, P REDICA T E, A1) and sentence b is in passive voice with sequence (A1, P R EDICAT E, A0). Addi- tional global preferences, ... argument instances. We chose a uniform Dirichlet prior with concentra- tion parameter as 0.1 for all the model parameters in Algorithm 1 (set roughly, without optimization 1 )....

Ngày tải lên: 19/02/2014, 19:20