Projects in the field of Information Extraction

• Connecting Information and Knowledge in Saarland.de (VIeWs)

• Data Intensive Semantics

• Semi-automatic segmentation and labelling for German (SALA)

• Web-based Intelligence for common-interest fiscal Networked Services (WINS)

• Multilingual Tourist Information on the World Wide Web (MIETTA)

• Integrated Digital Conference (InDiCo)

• Hybrid and Shallow Methods for Knowledge-Intensive Information Extraction (DEEP THOUGHT)

• Information Retrieval and Extraction Exercise (IREX)

• System for Large Scale Information Extraction (LaSIE)

• Designing Adaptive Information Extraction from Text for Knowledge Management (DOT.KOM)

• Quetal

• Recuperación de Información Textual en un Entorno Multilíngüe con Técnicas de Lenguaje Natural (ITEM)

• Cross-Lingual Multi-Agent Retail Comparison (CROSSMARC)

• RainbowII

• Innovation at the Call-Center (ICC)

• Terminology Extraction, Translation Tools and Comparable Corpora (TTC)

• Automatic creation of structured archives (ASTRA)

• Interactive Dynamic Information Extraction (IDEX)

• MENELAS

• Parameterizable Domain-Adaptive Information and Message Extraction (PARADIME)

• Knowledge Base for RTD competencies in IST (IST World)

• Cross-Lingual Multi-Agent Retail Comparison (CROSSMARC)

• a MUlti-Source Entity finder (MUSE)

• Technologies for Advanced Knowledge Extraction (TAKE)

• Proteus

• KnowMore

• A Multilingual Information Environment for Travel and Tourism Applications (MIETTA-II)

• BioMedical Text and Language Applications (BioTALA)

• Advanced Knowledge Technologies (AKT)

• Kernel Methods for Images and Text (KERMIT)

• WWW-based hypertexts for on-line scientific discussion and publication (Workbench)

• Collaboration in LAnguage and Speech Science and Technology (CLASS)

• World Wide Knowledge Base (WebKB) (WebKB)

• MULINEX

• Knowledge-Based Assistance for Requirements Analysis at Telekom (KARAT)

• HLT Opportunity Promotion in Europe (HOPE)

• Hybrid language processing technologies for a personal associative information access and management application (HyLaP)

• KnowItAll

• AIR FOReCast in Europe (AIRFORCE)

• Classifying Texts Integrating Pattern Matching and Information Extraction (FACILE)

• Annotation of Documents using Examples (ANNOCLASS)

• European Working Group on Discourse and Dialogue (DANDI)

• Finite-State Automa-based Text Understanding System (Fastus)

• Multilingual Text Tools and Corpora (Multext)

• Question Answering Collections (QA-Trec)

• Source Media Authoring Resources and Tools (SMART)

• Text Retrieval, Extraction and Summarisation for Large Enterprises (TRESTLE)

• Multilingual Content for Flexible Format Internet Premium Services (MEMPHIS)

• Designing Adaptive Information Extraction from Text for Knowledge Management (DOT.KOM)

• Multilinguale Konzepthierarchien zur Ordnung und Retrieval von medizinischen Informationen (MUCHMORE)

• Computational Linguistics and Language Technology for Real Life Applications (COLLATE)

• Genome Information Extraction (GenIE)

• Advanced data mining and integration research for Europe (ADMIRE)

• Terminology Extraction for Semantic Interoperability and Standardization (TExSIS)

• Foreign LAnguage Versions of Internet and User generated Sites (FLAVIUS)