Information Extraction, Focused Information Retrievel, and Question-Answering

The methods developed in this topic complement mainstream information retrieval techniques, whose main goal is document retrieval, by putting more emphasis on a precise analysis of text contents. Their are targeted for:

• Information extraction: spotting targeted information in texts, with entity and relation extraction
• Focused information retrieval: locating target information in documents to answer a query, and more
  specifically question-answering

Topics:

• Named-Entity recognition in general and specialized domain: recognition of complex NE types, dealing with lexical sparsity
• Relation extraction in general and specialized domain, with supervised and unsupervised approaches, based on surface and structured representations
• Event recognition and temporal information, thematic timelines
• Opinion mining: building of a lexicon
• Semantic inference and reasoning for answering question by searching a text or a knowledge base