Design And Performance Analysis Of A Factoid Question Answering System For Spontaneous Speech Transcriptions

This paper introduces a QA designed from scratch to handle speech transcriptions. The system's strength is achieved by analyzing the speech transcriptions with a mix of IR-oriented methodologies and a small number of robust NLP components. We evaluate the system on transcriptions of spontaneous speech from several 1-hour-long seminars and presentations and show that the system obtains encouraging performance.