Tài liệu Báo cáo khoa học: "Learning Hierarchical Translation Structure with Linguistic Annotations" ppt

... Computational Linguistics, pages 642–652, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Learning Hierarchical Translation Structure with Linguistic Annotations Markos ... syntactic parse structure, we opt for linguistically motivated translation. We learn latent hierarchical structure, taking advantage of linguistic annotations but shap...

Ngày tải lên: 20/02/2014, 04:20

... met- rics treat any divergence from the reference as a negative, while (computational) linguistics has long dealt with linguistic variation that preserves the meaning, usually called paraphrase, such ... into a more robust ensemble metric with linear regression. Our second, more fundamental, strategy replaces the use of loose surrogates of translation quality with a model that attem...

Ngày tải lên: 20/02/2014, 07:20

... More RBR-2 earlier Earlier later IN IN-0 In With After IN-1 In For At IN-2 in for on IN-3 of for on IN-4 from on with IN-5 at for by IN-6 by in with IN-7 for with on IN-8 If While As IN-9 because if ... matches with the max-rule parser is typically higher than with the Viterbi parser. (37.5% vs. 35.8% for our best grammar). These posterior rule probabilities are still given by (1)...

Ngày tải lên: 20/02/2014, 12:20

... by human annotators can be readily done. With our X-window based GUI, a typical table can be annotated with its boundary, column, and row demarcation within a minute. From these sample annotated ... that constitute tables. Lines with only space characters or special characters tend to delimit tables or are part of tables. Lines within a table tend to begin with some number of le...

Ngày tải lên: 20/02/2014, 19:20

... is a phrasal translation source that extracts translation pairs limited to the test sentences. For each source language n-gram within the pool, we have to find a set of candidate translations. ... confidence. Each candidate translation pair defines a partition within the sentence map, and this partitioning can be scored for confidence in translation quality. We estimate translation con-...

Ngày tải lên: 20/02/2014, 16:20

... interfaced with an existing, implemented transfer com- ponent (Verbmobi1), by translating f-structures into a term language, and by interfacing f- structure representations with an existing ... de- fined on term representations of f-structures. In the case of semantic transfer, transfer is de- fined on UDRS translations of f-structures. F- structure, term and UDRS correspondence...

Ngày tải lên: 20/02/2014, 18:20

... 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 multiple ... Computational Linguistics. Omar Zaidan. 2009. Z-MERT: A fully configurable open source tool for minimum error rate training of machine translation systems. In The Prague Bulletin of Mathe-...

Ngày tải lên: 19/02/2014, 19:20

... results line up with a traditional linguistic view of subcategorization, but this requires digging into the unsupervised out- 424 put and associating anonymous probabilistic objects with established ... possible predicate-argument structures. By combining the syntactic classes with unsupervised POS tagging (Teichert and Daum ´ e III, 2009) and the selectional preferences with distri...

Ngày tải lên: 19/02/2014, 19:20

... correct translation alternative, B: correct translation but with a difference sense from the reference, P: partially correct translation, and E: incorrect translation. Table 2 shows some translations ... described in Section 3.1.2 and 3.1.3. An example data generated with given term Emmy Award with features and translation/ non- translation labels is shown in Figure 1 usi...

Ngày tải lên: 19/02/2014, 19:20

... the sense with maximum inde- gree. Using the Indegree algorithm allows us to eas- ily replace the sense similarity with wmfvec. In In- degree, two senses are connected if their words are within ... 600. However, we cannot simply choose a hypothesis with the maximum R o − R m value, since v 3 , which is clearly not related to bank#n#1 but with a min- imum R m = 100, will therefore be (...

Ngày tải lên: 19/02/2014, 19:20