The QUANTUM Question Answering System

We participated to the TREC-X QA main task and list task with a new system named QUANTUM, which analyzes questions with shallow parsing techniques and regular expressions. Instead of using a question classification based on entity types, we classify the questions according to generic mechanisms (which we call extraction functions) for the extraction of candidate answers. We take advantage of the Okapi information retrieval system for one-paragraph-long passage retrieval. We make an extensive use of the Alembic named entity tagger and the WordNet semantic network to extract candidate answers from those passages. We deal with the possibility of noanswer questions (NIL) by looking for a significant score drop between the extracted candidate answers.

• Type: Conference
• Year: 2001
• Where: TREC
• Authors: Luc Plamondon, Guy Lapalme, Leila Kosseim
• Keywords: Candidate Answers, Extracted Candidate Answers, QA Main Task, TREC 2001, TREC 2008