Báo cáo khoa học: "Learning Translation Consensus with Structured Label Propagation" potx

... the translation performance significantly on both data sets, compared with a state-of-the-art baseline. 2 Graph-based Translation Consensus Our MT system with graph-based translation consensus ... graph-based model of translation consensus. Unlike Alexandrescu and Kirchhoff (2009), we reformulate the task of seeking translation consensus among source sentences as...

Ngày tải lên: 23/03/2014, 14:20

... LEARNING TRANSLATION SKILLS WITH A KNOWLEDGE-BASED TUTOR: FRENCH-ITALIAN CONJUNCTIONS IN CONTEXT Stefano A. Cerri ... classified as Unexpected Wrong: they do not have any relation in the knowledge base with the s.l. conjunction, nor with the concept in the question type considered. Notice that "concepts" ... student distinguishes between (112) and (CR) contexts, but...

Ngày tải lên: 18/03/2014, 02:20

... these raw scores with labels derived from Pareto optimality. 4 Experiments 4.1 Evaluation Methodology We experiment with two datasets: (1) The PubMed task is English-to-Japanese translation of ... 2006. A study of translation edit rate with targeted human annotation. In AMTA. Valentin I. Spitkovsky, Hiyan Alshawi, and Daniel Juraf- sky. 2011. Lateen em: Unsupervised training with...

Ngày tải lên: 19/02/2014, 19:20

... e(D, T) be the coverage rate of the feature set T with respect to a set of con- texts D, i.e., the ratio of the number of the occur- rences with at least one feature in their local con- texts ... helps to avoid the bias to- ward the selection of fewer features, since with fewer features, there are more occurrences without features in contexts, and their context vectors will be zero valu...

Ngày tải lên: 20/02/2014, 16:20

... motivate our ap- proach with examples of translation between En- glish and Japanese. 1 Introduction The focus of machine translation (MT) technol- ogy has been on the translation of sentence ... Figure 5: The IFG for NP Translation in an actual implementation. 5 A translation example We will now illustrate the proposed approach with a Japanese-to-English translation...

Ngày tải lên: 20/02/2014, 21:20

... scenarios, there were sig- nificant numbers of ESDs both with the minimum length of 5 and the maximum length of 16 and ev- erything in between. Combined with the fact that 93% of all individual event descriptions ... two phrases if they are semantically similar, i.e. it should cost more to align ‘exit’ with ‘eat’ than ‘exit’ with ‘leave’. Thus we take a measure of se- mantic (dis)simil...

Ngày tải lên: 07/03/2014, 22:20

... bijec- tively with those of α. • The terminal-labeled frontier nodes of γ are aligned (many-to-many) with those of α. In the substitution operation, an aligned pair of substitution nodes is rewritten with ... previous work (Chiang, 2007), with differences shown in Table 2. Rules with non- terminals were extracted from a subset of the data (labeled “Core” in Table 2), and rules witho...

Ngày tải lên: 07/03/2014, 22:20

... F 1 Random (with pruning) 13.1 11.0 12.0 Baseline 29.2 24.6 26.7 Model 1 25.2 46.9 32.8 Model 2’ 43.4 37.0 39.9 Model 2’ (with groups) 46.5 62.1 53.2 Graph matching (sup.) 73.4 64.5 68.6 Multilabel ... categor- ical fields. To annotate the data, we split the text by punc- tuation into lines and labeled each line with the records to which the line refers. These lines are used only for evalu...

Ngày tải lên: 17/03/2014, 01:20

... calculated as follows: S pos =  x 1{x label = positive} N (1) S pos =  x 1{x label = negative} N (2) where 1{x label = positive} is 1 if the tweet x is labeled positive, and N is the number ... contains over 476 million tweets la- beled with usernames and timestamps, collected through Twitter’s ‘spritzer’ API without keyword filtering. Tweets are aligned with polling data in Sectio...

Ngày tải lên: 24/03/2014, 03:20

... 2011. c 2011 Association for Computational Linguistics Discovering Sociolinguistic Associations with Structured Sparsity Jacob Eisenstein Noah A. Smith Eric P. Xing School of Computer Science Carnegie ... paper, we present a method to acquire such patterns from raw data. Us- ing multi-output regression with structured sparsity, our method identifies a small subset of lexical items tha...

Ngày tải lên: 17/03/2014, 00:20