Human language technology. challenges of the information society : third Language and Technology Conference, LTC 2007, Poznan, Poland, October 5-7, 2007 : revised selected papers

This book constitutes the refereed proceedings of the Third Language and Technology Conference: Human Language Technologies, LTC 2007, held in Poznan, Poland in October 5-7, 2007. The 40 revised papers presented were carefully reviewed and selected. The papers are organized in topical sections on speech processing, computational morphology, parsing and generation, computational semantics, digital language resources, WordNet, information retrieval/extraction and machine translation. Front Matter....Pages - Exploring the Structure of Broadcast News for Topic Segmentation....Pages 1-12 Application of Slope Filtering to Robust Spectral Envelope Extraction for Speech/Speaker Recognition....Pages 13-23 Spoken Language Interface for Mobile Devices....Pages 24-35 A Study on Bilingual Speech Recognition Involving a Minority Language....Pages 36-49 Annotated Corpus of Polish Spoken Dialogues....Pages 50-62 Triphone Statistics for Polish Language....Pages 63-73 ROG – A Paradigmatic Morphological Generator for Romanian....Pages 74-84 Building a Morphosyntactic Lexicon and a Pre-syntactic Processing Chain for Polish....Pages 85-95 A Relational Model of Polish Inflection in Grammatical Dictionary of Polish ....Pages 96-106 Syntactic Spreadsheets: In Search for a Human-Readable Representation of Parse Tree Forests....Pages 107-117 A Hybrid System for Named Entity Metonymy Resolution....Pages 118-130 Spejd: A Shallow Processing and Morphological Disambiguation Tool....Pages 131-141 Flexible Natural Language Generation in Multiple Contexts....Pages 142-153 A Measure of the Number of True Analogies between Chunks in Japanese....Pages 154-164 Shallow Parsing of Transcribed Speech of Estonian and Disfluency Detection....Pages 165-177 Mining Parsing Results for Lexical Correction: Toward a Complete Correction Process of Wide-Coverage Lexicons....Pages 178-191 Efficient Parsing Using Recursive Transition Networks with Output....Pages 192-204 The Deep Parser for Polish....Pages 205-217 Automatically Determining Attitude Type and Force for Sentiment Analysis....Pages 218-231 A Readability Checker Based on Deep Semantic Indicators....Pages 232-244 The DANTE Temporal Expression Tagger....Pages 245-257 Hybrid Unsupervised Learning to Uncover Discourse Structure....Pages 258-269 Pronoun Resolution in Turkish Using Decision Tree and Rule-Based Learning Algorithms....Pages 270-278 LMF-QL: A Graphical Tool to Query LMF Databases for NLP and Editorial Use....Pages 279-290 Novelty Extraction from Special and Parallel Corpora....Pages 291-302 Construction of Text Corpus of Polish Using the Internet....Pages 303-311 A Predicate Database for Assisting the Design of a Lexicon-Grammar of Predicative Nouns....Pages 312-324 A Standard Lexical-Terminological Resource for the Bio Domain....Pages 325-335 Extracting Collocations in Contexts....Pages 336-349 Putting Semantics into WordNet’s "Morphosemantic" Links....Pages 350-358 Leveraging Parallel Corpora and Existing Wordnets for Automatic Construction of the Slovene Wordnet....Pages 359-368 An Algorithm for Building Lexical Semantic Network and Its Application to PolNet - Polish WordNet Project....Pages 369-381 ECODE: A Definition Extraction System....Pages 382-391 Using Graph-Based Indexing to Identify Subject-Shift in Topic Tracking....Pages 392-404 Result Aggregation for Knowledge-Intensive Multicultural Name Matching....Pages 405-412 Comparison of String Distance Metrics for Lemmatisation of Named Entities in Polish....Pages 413-427 An Iterative Model for Discovering Person Coreferences Using Name Frequency Estimates....Pages 428-439 Hapax Legomena : Their Contribution in Number and Efficiency to Word Alignment....Pages 440-450 Statistical Machine Translation from Slovenian to English Using Reduced Morphology....Pages 451-460 Semi-automatic Creation of a Dictionary of Nominal Compounds....Pages 461-469 Back Matter....Pages - Half a centuryago not manypeople had realizedthat a new epoch in the history of homo sapiens had just started. The term “Information Society Age” seems an appropriate name for this epoch. Communication was without a doubt a lever of the conquest of the human race over the rest of the animate world. There is little doubt that the human racebegan when our predecessorsstarted to communicate with each other using language.This highly abstractmeans of communicationwas probably one of the major factors contributing to the evolutionary success of the human race within the animal world. Physically weak and imperfect, humans started to dominate the rest of the world through the creation of communication-based societies where individuals communicated initially to satisfy immediate needs, and then to create, accumulate and process knowledge for future use. The crucial step in the history of humanity was the invention of writing. It is worth noting that writing is a human invention, not a phenomenon resulting from natural evolution. Humans invented writing as a technique for recording speech as well as for storing and facilitating the dissemination of knowledge across the world. Humans continue to be born illiterate, and therefore teaching and conscious supervised learning is necessary to maintain this basic social skill.