Ebook: 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.

---

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.

---

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.

Content:
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
Syntactic Spreadsheets: In Search for a Human-Readable Representation of Parse Tree Forests....Pages 96-106
A Hybrid System for Named Entity Metonymy Resolution....Pages 107-117
Spejd: A Shallow Processing and Morphological Disambiguation Tool....Pages 118-130
Flexible Natural Language Generation in Multiple Contexts....Pages 131-141
A Measure of the Number of True Analogies between Chunks in Japanese....Pages 142-153
Shallow Parsing of Transcribed Speech of Estonian and Disfluency Detection....Pages 154-164
Mining Parsing Results for Lexical Correction: Toward a Complete Correction Process of Wide-Coverage Lexicons....Pages 165-177
Efficient Parsing Using Recursive Transition Networks with Output....Pages 178-191
The Deep Parser for Polish....Pages 192-204
Automatically Determining Attitude Type and Force for Sentiment Analysis....Pages 205-217
A Readability Checker Based on Deep Semantic Indicators....Pages 218-231
The DANTE Temporal Expression Tagger....Pages 232-244
Hybrid Unsupervised Learning to Uncover Discourse Structure....Pages 245-257
Pronoun Resolution in Turkish Using Decision Tree and Rule-Based Learning Algorithms....Pages 258-269
LMF-QL: A Graphical Tool to Query LMF Databases for NLP and Editorial Use....Pages 270-278
Novelty Extraction from Special and Parallel Corpora....Pages 279-290
Construction of Text Corpus of Polish Using the Internet....Pages 291-302
A Predicate Database for Assisting the Design of a Lexicon-Grammar of Predicative Nouns....Pages 303-311
A Standard Lexical-Terminological Resource for the Bio Domain....Pages 312-324
Extracting Collocations in Contexts....Pages 325-335
Putting Semantics into WordNet’s "Morphosemantic" Links....Pages 336-349
Leveraging Parallel Corpora and Existing Wordnets for Automatic Construction of the Slovene Wordnet....Pages 350-358
An Algorithm for Building Lexical Semantic Network and Its Application to PolNet - Polish WordNet Project....Pages 359-368
ECODE: A Definition Extraction System....Pages 369-381
Using Graph-Based Indexing to Identify Subject-Shift in Topic Tracking....Pages 382-391
Result Aggregation for Knowledge-Intensive Multicultural Name Matching....Pages 392-404
Comparison of String Distance Metrics for Lemmatisation of Named Entities in Polish....Pages 405-412
An Iterative Model for Discovering Person Coreferences Using Name Frequency Estimates....Pages 413-427
Statistical Machine Translation from Slovenian to English Using Reduced Morphology....Pages 428-439
Semi-automatic Creation of a Dictionary of Nominal Compounds....Pages 440-450
Back Matter....Pages 451-460
....Pages 461-469