Báo cáo khoa học: "Combining Trigram and Winnow in Thai OCR Error Correction" potx
... Combining Trigram and Winnow in Thai OCR Error Correction Surapant Meknavin National Electronics and Computer Technology Center 73/1 Rama VI Road, Rajthevi, Bangkok, Thailand surapan@nectec.or.th ... are intro- duced in the text. The existing approach for correcting the spelling error in the languages that have no word boundary assumes that all substrings in i...
Ngày tải lên: 23/03/2014, 19:20
... in the back of Random House (Flexner, 1983). The con- fusion sets were selected on the basis of being frequently-occurring in Brown, and representing a variety of types of errors, including ... Spelling errors that result in valid, though unin- tended words, have been found to be very common in the production of text. Such errors were thought to be too difficult to handle an...
Ngày tải lên: 23/03/2014, 20:21
... for manipulating data. Objects can be classified into classes and instances. A class defines a procedure [called a method) for handling incoming messages of its instances. A class inherits methods ... flexible means of abstracting modules and sharing common knowledge. 1. Introduction The goal of this paper is to elaborate a domain-independent way of organizing linguistic knowledge...
Ngày tải lên: 21/02/2014, 20:20
Báo cáo khoa học: "Combining Statistical and Knowledge-based Spoken Language Understanding in Conditional Models" pptx
... joint expertise in natural language processing and speech recognition, and best practices in language engineering for every new domain. On the other hand, a statistical learning approach needs ... in natural language processing and speech recognition, and best practices in language engineering for every new domain. In the past decade many statistical learning approa...
Ngày tải lên: 08/03/2014, 02:21
Báo cáo khoa học: "Combining Acoustic and Pragmatic Features to Predict Recognition Performance in Spoken Dialogue Systems" pdf
... Randomly split the remaining data into an 80% training and 20% test set. 3. Run TiMBL with all possible parameter set- tings on the generated training and test sets and store the best performing ... – an interactive (i.e. mouse click- able) map – and specifies mission goals using nat- ural language commands spoken into a headset, or by using combinations of GUI actions and spoken com...
Ngày tải lên: 08/03/2014, 04:22
Báo cáo khoa học: "Combining Stochastic and Rule-Based Methods for Disambiguation in Agglutinative Languages" pptx
Ngày tải lên: 08/03/2014, 05:21
Báo cáo khoa học: "Combining data and mathematical models of language change" ppt
... languages: The effects of bilingualism and social structure. Lingua, 118(1):19–45. D. Minkova. 1997. Constraint ranking in Middle En- glish stress-shifting. English Language and Linguis- tics, 1(1):135–175. W.G. ... coupled. In Model 1 there is no coupling (ˆα t and ˆ β t learned independently), in Models 2–3 coupling takes the form of a hard constraint corresponding to Ross’ gene...
Ngày tải lên: 17/03/2014, 00:20
Báo cáo khoa học: "Combining Deep and Shallow Approaches in Parsing German" pptx
... selected certain readings become undistinguishable. Rather, in or- der to distinguish a maximum number of readings, pre-modifiers must attach to the last conjunct and post-modifiers and coordinating conjunctions ... verb, preposition and head noun into a triple, and thus only count content words in the evaluation. For learning, the matter can be resolved empirically: 2 Even in thi...
Ngày tải lên: 17/03/2014, 06:20
Báo cáo khoa học: "Combining Linguistic and Gaze Features to Resolve Second-Person References in Dialogue" docx
... referential and generic uses of you. Then, within the referential uses, we dis- tinguish between singular and plural, and finally, we resolve the singular referential instances by identifying the intended ... when addressing the group, thus drawing the listeners’ gaze in this direction. Future work will involve expanding our data- set, and investigating new potentially predictive fea...
Ngày tải lên: 17/03/2014, 22:20
Báo cáo khoa học: "Combining Source and Target Language Information for Name Tagging of Machine Translation Output" ppt
... performance on machine translated text, because of the poor syntax of the MT output and other errors in the translation. As some tagging distinctions are clearer in the source, and some in the target, ... ORGANIZATION, GPE and LOCATION, and so a total of 9 states. 4.4 Feature Sets for MEMM In our experiment, we are interested not only in training a module, but also i...
Ngày tải lên: 31/03/2014, 00:20