Human Language Technology Challenges for Computer Science and Linguistics

This book constitutes the refereed proceedings of the 5th Language and Technology Conference: Challenges for Computer Science and Linguistics, LTC 2011, held in Poznan, Poland, in November 2011. The 44 revised and in many cases substantially extended papers presented in this volume were carefully reviewed and selected from 111 submissions. The focus of the papers is on the following topics: speech, parsing, computational semantics, text analysis, text annotation, language resources: general issues, language resources: ontologies and Wordnets and machine translation.

Includes supplementary material: sn.pub/extras

Inhalt

Active Learning to Speed-up the Training Process for Dialogue Act Labelling.- Direct and Word graph-based Confidence Measures in Dialogue Annotation with N-Gram Transducers.- Orwell's 1984 from Simple to Multi-Word Units.- Application of Audio and Video Processing Methods for Language Research and Documentation. The AVA Tech Project.- Language Resources: General Issues.- Crowdsourcing for Language Resource Development: Criticisms about Amazon Mechanical Turk Overpowering Use.- Extending a Tool Resource Framework with U-Compare.- Language Resources: Ontologies and Wordnets.- Aligning GermaNet Senses with Wiktionary Sense Definitions.- A Tool for Transforming Word Net-like Databases.- KABA Subject Heading Language as the Main Resource Subject Organization Tool in a Semantic Knowledge Base.- Enhancing tagging systems by word net based ontologies.- Natural Language Ontology of Action. A gap with huge consequences for Natural Language Understanding and Machine Translation.- Classification-based extension of word nets from heterogeneous resources.- Pol Net Polish Word Net.- Machine Translation.- Improving the Distribution of N-grams in Phrase Tables Obtained by the Sampling-based Method.- Marker-based Chunking in Eleven European Languages for Analogy-based Translation.- Comparing CBMT Approaches for German-Romanian.- Text Genre- An Unexplored Parameter in Statistical Machine Translation.- Problems concerning Less Resourced Languages Detecting Gaps in Language Resources and Tools in the Project CESAR.- A first LVCSR system for Luxembourgish, a low-resourced European Language.- Developing LRs for Non-Scheduled Indian Languages A Case of Magahi.- Quizzes on Tap: Exporting a Test Generation System from one Less-Resourced Language to Another.- A Multilingual Text Normalization Approach.- Creating Multilingual Parallel Corpora in Indian Languages.- Inducing grammars from IGT.