Abstract
While increasingly complex approaches to question answering (QA) have been proposed, the true gain of these systems, particularly with respect to their expensive training requirements, can be in- flated when they are not compared to adequate baselines. Here we propose an unsupervised, simple, and fast alignment and informa- tion retrieval baseline that incorporates two novel contributions: a one-to-many alignment between query and document terms and negative alignment as a proxy for discriminative information. Our approach not only outperforms all conventional baselines as well as many supervised recurrent neural networks, but also approaches the state of the art for supervised systems on three QA datasets. With only three hyperparameters, we achieve 47% P@1 on an 8th grade Science QA dataset, 32.9% P@1 on a Yahoo! answers QA dataset and 64% MAP on WikiQA.
Original language | English (US) |
---|---|
Title of host publication | 41st International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018 |
Publisher | Association for Computing Machinery, Inc |
Pages | 1217-1220 |
Number of pages | 4 |
ISBN (Electronic) | 9781450356572 |
DOIs | |
State | Published - Jun 27 2018 |
Event | 41st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018 - Ann Arbor, United States Duration: Jul 8 2018 → Jul 12 2018 |
Other
Other | 41st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2018 |
---|---|
Country | United States |
City | Ann Arbor |
Period | 7/8/18 → 7/12/18 |
Keywords
- Answer reranking
- Information retrieval
- Question answering
- Unsupervised system
ASJC Scopus subject areas
- Software
- Computer Graphics and Computer-Aided Design
- Information Systems