Recent advancements in transformer-based models have greatly improved the ability of Question Answering (QA) systems to provide correct answers; in particular, answer sentence selection (AS2) models, core components of retrieval-based systems, have achieved impressive results. While generally effective, these models fail to provide a satisfying answer when all retrieved candidates are of poor quality, even if they contain correct information. In AS2, models are trained to select the best answer sentence among a set of candidates retrieved for a given question. In this work, we propose to generate answers from a set of AS2 top candidates. Rather than selecting the best candidate, we train a sequence to sequence transformer model to generate an answer from a candidate set. Our tests on three English AS2 datasets show improvement up to 32 absolute points in accuracy over the state of the art.
@article{arxiv.2106.00955,
title = {Answer Generation for Retrieval-based Question Answering Systems},
author = {Chao-Chun Hsu and Eric Lind and Luca Soldaini and Alessandro Moschitti},
journal= {arXiv preprint arXiv:2106.00955},
year = {2021}
}