Spoken Question Answering on Municipal Council Meetings
摘要
We demo an IR system for municipal council meetings only available in video format. The system uses Whisper to turn speech into text. Three IR systems were compared in a user study: BM25/TF-IDF, KNN ranking on MPNet embeddings, and a chatbot prompted with the query and the top k highly ranked passages. Users solved complex information need slightly faster using the chatbot, but did not find the correct answer in 23%, whereas these were always found with the BM25 and KNN rankers. The benefits of the IR system compared to no system were huge: problem solving time dropped from around 2 min to half a minute and the miss rate from 69% to 0%.