Text, Speech and Dialogue

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.