The LIMSI Multilingual, Multitask QAst System
In this paper, we present the LIMSI question-answering system which participated to the Question Answering on speech transcripts 2008 evaluation. This systems is based on a complete and multi-level analysis of both queries and documents. It uses an automatically generated research descriptor. A score based on those descriptors is used to select documents and snippets. The extraction and scoring of candidate answers is based on proximity measurements within the research descriptor elements and a number of secondary factors. We participated to all the subtasks and submitted 18 runs (for 16 sub-tasks). The evaluation results for manual transcripts range from 31% to 45% for accuracy depending on the task and from 16 to 41% for automatic transcripts.
Unable to display preview. Download preview PDF.
- 1.Déchelotte, D., Schwenk, H., Adda, G., Gauvain, J.-L.: Improved machine translation of speech-to-text outputs, Antwerp. Belgium (2007)Google Scholar
- 2.Rosset, S., Galibert, O., Adda, G., Bilinski, E.: The limsi qast systems: comparison between human and automatic rules generation for question-answering on speech transcriptions. In: IEEE ASRU (December 2007)Google Scholar