Báo cáo khoa học: "Learning to Translate with Source and Target Syntax" pot

Báo cáo khoa học: "Learning to Translate with Source and Target Syntax" pot

Báo cáo khoa học: "Learning to Translate with Source and Target Syntax" pot

... similar to the expanded set recently used for Hiero (Chiang et al., 2009), but with bigram features (source and target word) instead of trigram features (source and target word and neighboring source ... translation. The decoder has to store in each hypothesis the source and target root labels of the partial derivation, but these la- bels are used for calculating fea...

Ngày tải lên: 07/03/2014, 22:20

10 377 0
Tài liệu Báo cáo khoa học: "Learning to Translate with Multiple Objectives" doc

Tài liệu Báo cáo khoa học: "Learning to Translate with Multiple Objectives" doc

... weight vector w, takes in a foreign sen- tence f and returns a translated hypothesis h. The argmax operates in vector space and our goal is to find w leading to hypotheses on the Pareto Frontier. In ... approach to optimiza- tion: i.e. optimizing towards points on the Frontier and away from those that are not, and giving no pref- erence to different pareto-optimal hypotheses. 2...

Ngày tải lên: 19/02/2014, 19:20

10 624 0
Báo cáo khoa học: "Learning to predict pitch accents and prosodic boundaries in Dutch" ppt

Báo cáo khoa học: "Learning to predict pitch accents and prosodic boundaries in Dutch" ppt

... different annotators, and were corrected in a second stage, again without over- lap, by two corrector-annotators. The annotators’ task was to indicate the locations of accents and/ or breaks that ... occurs in, with n ranging from 1 to 25, and computed in an iterative growth procedure: log- likelihoods of n + 1-grams were computed by ex- panding all stored n-grams one word to the...

Ngày tải lên: 17/03/2014, 06:20

8 462 0
Báo cáo khoa học: "Learning to Identify Fragmented Words in Spoken Discourse" pot

Báo cáo khoa học: "Learning to Identify Fragmented Words in Spoken Discourse" pot

... decision trees and language models to detect disfluency events (Stolcke et al., 1998) or to model repairs reparandum 2 interruption point repair 25 (Heeman, 1999). Although Spilker et al. (2001) and Heeman ... con- text (R1 and R2), and the left context (L1 and L2). On the other hand, the gain ratio metric assigns the highest weight to the overlap between the first letter...

Ngày tải lên: 31/03/2014, 20:20

8 329 0
Tài liệu Báo cáo khoa học: "Learning to Find Translations and Transliterations on the Web" doc

Tài liệu Báo cáo khoa học: "Learning to Find Translations and Transliterations on the Web" doc

... engine, and automatically annotating the snippets with tags and features for training a conditional random field model. At run- time, the model is used to extracting translation candidates ... Emmy Awards) to query a search engine with the target webpage language set to the target language (e.g., Chinese), biasing the search engine to return Chinese webpages interspe...

Ngày tải lên: 19/02/2014, 19:20

5 532 1
Tài liệu Báo cáo khoa học: "Learning to Follow Navigational Directions" pdf

Tài liệu Báo cáo khoa học: "Learning to Follow Navigational Directions" pdf

... function and can be applied to domains with stochastic transitions, such as robot locomotion. 808 4.2 Action An action a ∈ A is composed of a named land- mark l, the target of the action, together with ... in) and allocentric (on which side we pass a landmark), combined with each spatial word. Allocentric terms such as above and below tend to be interpreted as going to the...

Ngày tải lên: 20/02/2014, 04:20

9 527 0
Tài liệu Báo cáo khoa học: "Learning to Compose Effective Strategies from a Library of Dialogue Components" doc

Tài liệu Báo cáo khoa học: "Learning to Compose Effective Strategies from a Library of Dialogue Components" doc

... 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 ... 2002; Peek and Chickering, 2005; Frampton and Lemon, 2006), for selecting initiative and con- firmation strategies (Singh et al., 2002); for detect- ing speech recognition problem (L...

Ngày tải lên: 20/02/2014, 12:20

8 418 0
Tài liệu Báo cáo khoa học: "Learning Word Senses With Feature Selection and Order Identification Capabilities" pdf

Tài liệu Báo cáo khoa học: "Learning Word Senses With Feature Selection and Order Identification Capabilities" pdf

... conducted to reduce the di- mensionality of context vectors. Then the reduced context vectors were grouped into a pre-defined number of clusters whose centroids corresponded to senses of target word. Some ... contextual word’s vectors together may result in noise-dominated second or- der context vectors. To deal with this problem, we extend the feature selection procedure further to...

Ngày tải lên: 20/02/2014, 16:20

8 463 0
Tài liệu Báo cáo khoa học: "Learning to Recognize Tables in Free Text" pptx

Tài liệu Báo cáo khoa học: "Learning to Recognize Tables in Free Text" pptx

... about 6 and 30 mil (between about 6 and 30 point chip board). Insulation Mineral wool, having a density of between 2.5 and 6.0 pounds per cubic foot and a thickness of between 1/4 and 1 and ... category, and these are the kinds of texts that our approach to table recognition handles. The work of (Hurst and Douglas, 1997; Douglas and Hurst, 1996; Douglas et al., 1995...

Ngày tải lên: 20/02/2014, 19:20

8 495 0
w