Revisiting the Open-Domain Question Answering Pipeline

Open-domain question answering (QA) is the tasl of identifying answers to natural questions from a large corpus of documents. The typical open-domain QA system starts with information retrieval to select a subset of documents from the corpus, which are then processed by a machine reader to select th...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Semnani, Sina J, Pandey, Manish
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 02.09.2020
Subjects
Domains
Information retrieval
Pipelines
Questions
Relevance feedback
Online AccessGet full text

Cover

More Information
Summary:Open-domain question answering (QA) is the tasl of identifying answers to natural questions from a large corpus of documents. The typical open-domain QA system starts with information retrieval to select a subset of documents from the corpus, which are then processed by a machine reader to select the answer spans. This paper describes Mindstone, an open-domain QA system that consists of a new multi-stage pipeline that employs a traditional BM25-based information retriever, RM3-based neural relevance feedback, neural ranker, and a machine reading comprehension stage. This paper establishes a new baseline for end-to-end performance on question answering for Wikipedia/SQuAD dataset (EM=58.1, F1=65.8), with substantial gains over the previous state of the art (Yang et al., 2019b). We also show how the new pipeline enables the use of low-resolution labels, and can be easily tuned to meet various timing requirements.
ISSN:2331-8422