Team LeD

Overall Objectives
Scientific Foundations
Application Domains
New Results
Other Grants and Activities

Section: New Results

Textual Entailment

Participants : Carlos Areces, Paul Bedaride, Claire Gardent.

One important characteristic of natural language is the huge flexibility on the ways in which we can express the same information. Many NLP applications like Question/Answering, information retrieval, and so on, need to deal with this diversity efficiently and accurately. Recognizing textual entailment, i.e., the question of whether the information contained in a given text T1 can be inferred from the information provided by another text T2 , is the core inference task for such systems.

Textual entailment recognition is a very difficult task, and systems presented at conferences like the RTE Challenge ( ) still perform very poorly.

LED has recently started investigating this issue, and Paul Bedaride's Master Thesis [48] investigates how lexical information encoded as a description logic ontology can be used in this task.


Logo Inria