Báo cáo khoa học: "TEXTUAL EXPERTISE IN WORD EXPERTS: AN APPROACH TO TEXT PARSING BASED ON TOPIC/COMMENT MONITORING" potx

Báo cáo khoa học: "TEXTUAL EXPERTISE IN WORD EXPERTS: AN APPROACH TO TEXT PARSING BASED ON TOPIC/COMMENT MONITORING" potx

Báo cáo khoa học: "TEXTUAL EXPERTISE IN WORD EXPERTS: AN APPROACH TO TEXT PARSING BASED ON TOPIC/COMMENT MONITORING" potx

... TEXTUAL EXPERTISE IN WORD EXPERTS: AN APPROACH TO TEXT PARSING BASED ON TOPIC/COMMENT MONITORING * Udo Hahn Universitaet Konstanz Informationswissenschaft ProJekt TOPIC Postfach ... topics instead of topic graphs) (HAHN/REIMER 1984). 5. Conclusion In this paper we have argued in favor of a word expert approach to text parsing based on the noti...

Ngày tải lên: 31/03/2014, 17:20

7 314 0
Báo cáo khoa học: "Automatic Editing in a Back-End Speech-to-Text System" doc

Báo cáo khoa học: "Automatic Editing in a Back-End Speech-to-Text System" doc

... the 115 archived dictations recognize  new dictation recognize  store oo transcripts @A train // transcript transform  transformation model // targets GF // tokens format  archived documents tokenize OO draft document manual correction  final document @A store OO Figure 1: Illustration of how text transformation is inte- grated into a speech -to- text system. inverse of tokenizat...

Ngày tải lên: 17/03/2014, 02:20

7 363 0
Báo cáo khoa học: "A Generative Blog Post Retrieval Model that Uses Query Expansion based on External Collections" potx

Báo cáo khoa học: "A Generative Blog Post Retrieval Model that Uses Query Expansion based on External Collections" potx

... Introduction One of the grand challenges in information re- trieval is to bridge the vocabulary gap between a user and her information need on the one hand and the relevant documents on the other ... is to expand the query using global collection statistics based, for instance, on a co-occurrence analysis of the en- tire collection. Thesaurus- and dictionary -based expansion as...

Ngày tải lên: 30/03/2014, 23:20

9 314 0
Báo cáo khoa học: " Contextual Analysis in Word-for-word MT" pot

Báo cáo khoa học: " Contextual Analysis in Word-for-word MT" pot

... structural context and meaning, and that the barest kind of routine comparison re- sults in a high (although not absolute) degree of accuracy in the determination of meaning. Non-structural ... limited to the imme- diately contiguous word in the sentence (the pre-x or post-x word) . Without attempting to rearrange the word order of the Russian sen- tence, one can obtai...

Ngày tải lên: 23/03/2014, 13:20

2 202 0
Báo cáo khoa học: Universal positions in globular proteins From observation to simulation ppt

Báo cáo khoa học: Universal positions in globular proteins From observation to simulation ppt

... close in space, to avoid clustering due to particular initial state conformation. Quantitatively, this constraint introduces a minimum spatial distance, dmin, according to the separ- ation Delta ... NMR analysis of folding intermediates of protein bovine pancreatic trypsine inhibitor [25] revealed loop formation i n early, non-native states, stabilized by nonlocal interactions. Also,...

Ngày tải lên: 07/03/2014, 16:20

7 384 0
Báo cáo khoa học: "A Method for Word Sense Disambiguation of Unrestricted Text" potx

Báo cáo khoa học: "A Method for Word Sense Disambiguation of Unrestricted Text" potx

... sentence context. The words are paired and an attempt is made to disambiguate one word within the context of the other word. This is done by searching on Internet with queries formed using different ... and discourse contexts and is based on the idea of semantic distance between words, and lexical relations. It uses WordNet and it was tested on SemCor. Table 4 presents t...

Ngày tải lên: 08/03/2014, 06:20

7 378 0
Báo cáo khoa học: "Recognizing Authority in Dialogue with an Integer Linear Programming Constrained Model" pptx

Báo cáo khoa học: "Recognizing Authority in Dialogue with an Integer Linear Programming Constrained Model" pptx

... model to function as an on- line classifier. We build two segmentation models, one trained on contributions of less than four tokens, and an- other trained on contributions of four or more to- kens, ... “dominant” - statements of fact or opinion, and commands or instructions - and two that appear less dominant - questions or requests for information, and narration of an action....

Ngày tải lên: 23/03/2014, 16:20

9 442 0
Báo cáo khoa học: "The Benefit of Stochastic PP Attachment to a Rule-Based Parser" doc

Báo cáo khoa học: "The Benefit of Stochastic PP Attachment to a Rule-Based Parser" doc

... bilingual, aligned English- Japanese corpus. They used this information to re- attach PPs in a machine translation system, report- ing an improvement in translation quality when translating into ... to it. Also, the syntac- tical configuration in this standard benchmark is not the predominant one in complete German sen- tences; in fact fewer than 10% of all prepositions occur...

Ngày tải lên: 17/03/2014, 04:20

8 331 0
Báo cáo khoa học: "A Non-negative Matrix Tri-factorization Approach to Sentiment Classification with Lexical Prior Knowledge" potx

Báo cáo khoa học: "A Non-negative Matrix Tri-factorization Approach to Sentiment Classification with Lexical Prior Knowledge" potx

... rec- ommendations for products and services, guid- ing their own choices and decisions by the opin- ions that other consumers have publically ex- pressed. Gleaning insights by monitoring and an- alyzing ... vectors, one corresponding to positive words and another corresponding to negative words. This yields a two-dimensional representation for docu- ments, on which we then perform K-m...

Ngày tải lên: 30/03/2014, 23:20

9 459 0
Báo cáo khoa học: "Unsupervised Topic Identification by Integrating Linguistic and Visual Information Based on Hidden Markov Models" potx

Báo cáo khoa học: "Unsupervised Topic Identification by Integrating Linguistic and Visual Information Based on Hidden Markov Models" potx

... identification, wherein a state corre- sponds to a topic, like preparation and frying, and various features, which include visual and audio information as well as linguistic information (in- structor’s ... necessary to seg- ment them into meaningful segments and annotate them. Because manual annotation is extremely ex- pensive and timeconsuming, automatic annotation technique is required....

Ngày tải lên: 31/03/2014, 01:20

8 354 0
w