Báo cáo khoa học: "Learning to Say It Well: Reranking Realizations by Predicted Synthesis Quality" pdf

... Linguistics Learning to Say It Well: Reranking Realizations by Predicted Synthesis Quality Crystal Nakatsu and Michael White Department of Linguistics The Ohio State University Columbus, OH 43210 ... is to have the system choose what to say in part by taking into account what is likely to sound natural when synthesized. The idea is to take advantage of the genera...

Ngày tải lên: 31/03/2014, 01:20

... attention to some limitations and opportunities raised by this work: Limitations: (1) The performance of PMO is limited by the size of the Pareto set. Small N-best lists lead to sparsely-sampled Pareto ... pareto vs. non-pareto points ignores the fact that 2nd-place non-pareto points may also lead to good practical solutions. A better approach may be to adopt a graded definition of...

Ngày tải lên: 19/02/2014, 19:20

... (EM) algorithm to align English syllables Romanized Chinese characters. Finally, we use the alignment information to generate transliteration feature for a Chinese token with respect to English ... potentially be used to assist translators to find the most common translation for a given term, or to supplement a bilingual terminology bank (e.g., adding multilingual titles to...

Ngày tải lên: 19/02/2014, 19:20

... and it is her task to describe the path to the instruction follower, who cannot see the reference path. Our system learns to interpret these navigational direc- tions, without access to explicit ... a)]. To learn these weights θ we use SARSA (Sutton and Barto, 1998), an online learn- ing algorithm similar to Q-learning (Watkins and Dayan, 1992). Algorithm 1 details the learning...

Ngày tải lên: 20/02/2014, 04:20

... generally been limited to well defined areas of the dialogue, in particular dealing with speech recognition and clarification problems, with small state spaces and a limited set of actions to choose from ... is to listen to the user. This paper de- scribes the development of an adaptive dialogue sys- tem that uses the feedback of users to automatically improve its strategy. The system...

Ngày tải lên: 20/02/2014, 12:20

... assigned by the human annotator to the class assigned by our ta- ble recognition program on every hline of the text. Let A be the number of hlines identified by the hu- man annotator as being ... within the table are then grouped together to form the columns. 4.2.3 Row The deterministic algorithm to recognize table row is similar to the recognition algorithm of the learn...

Ngày tải lên: 20/02/2014, 19:20

Ngày tải lên: 22/02/2014, 03:20

... a compromise by continuing to al- low SAMT-style complex categories, but commit- ting to a single analysis by requiring all phrases to nest. To do this, we use a simple heuristic. Iterate through ... 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...

Ngày tải lên: 07/03/2014, 22:20

... se- lected as the one corresponding to the roll-out with the best final utility. See Algorithm 1 for details. The success of Monte-Carlo search is based on its ability to make a fast, local estimate ... available where a population settles affects its ability to produce food and goods. Build your city on a plains or grassland square with a river running through it if possible. Figure...

Ngày tải lên: 07/03/2014, 22:20

... at http://nlp.stanford.edu/software/dependencies manual .pdf 754 less inherent similarity. It remains to be determined how much of a node’s subgraph will positively en- rich its semantics. In addition to the complete N 0 x subgraph, we chose to ... fo- cus of this work. An automatic short answer grading system is one that automatically assigns a grade to an answer pro- vided by a...

Ngày tải lên: 07/03/2014, 22:20