Text, Speech and Dialogue 17th International Conference, TSD 2014, Brno, Czech Republic, September 8-12, 2014. Proceedings /

• Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
• Άλλοι συγγραφείς: Sojka, Petr (Επιμελητής έκδοσης), Horák, Aleš (Επιμελητής έκδοσης), Kopeček, Ivan (Επιμελητής έκδοσης), Pala, Karel (Επιμελητής έκδοσης)
• Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: Cham : Springer International Publishing : Imprint: Springer, 2014.
• Σειρά: Lecture Notes in Computer Science, 8655
• Θέματα: Computer science.; Database management.; Data mining.; Information storage and retrieval.; Artificial intelligence.; Pattern recognition.; Computer Science.; Artificial Intelligence (incl. Robotics).; Information Systems Applications (incl. Internet).; Information Storage and Retrieval.; Database Management.; Pattern Recognition.; Data Mining and Knowledge Discovery.

This book constitutes the refereed proceedings of the 17th International Conference on Text, Speech and Dialogue, TSD 2013, held in Brno, Czech Republic, in September 2014. The 70 papers presented together with 3 invited papers were carefully reviewed and selected from 143 submissions. They focus on...

Πίνακας περιεχομένων:

• Empiric Introduction to Light Stochastic Binarization
• Comparative Study Concerning the Role of Surface Morphological Features in the Induction of Part-of-Speech Categories
• Automatic Adaptation of Author’s Stylometric Features to Document Types
• Detecting Commas in Slovak Legal Texts
• Detection and Classification of events in Hungarian natural language texts
• Generating Underspecified Descriptions of Landmark Objects
• A Topic Model Scoring Approach for Personalized QA Systems
• Feature Exploration for Authorship Attribution of Lithuanian Parliamentary Speeches
• Processing of Quantitative Expressions with Measurement Units in the Nominative, Genitive, and Accusative Cases for Belarusian and Russian
• Document Classification with Deep Rectifier Neural Networks and Probabilistic Sampling
• Sentence Similarity by Combining Explicit Semantic Analysis and Overlapping N-grams.