Answer Generation for Retrieval-based Question Answering Systems

TL;DR

This paper introduces a novel approach for retrieval-based question answering by generating answers from candidate sets using a sequence-to-sequence transformer, significantly improving accuracy over existing methods.

Contribution

It proposes a new answer generation method from candidate sets, surpassing traditional answer selection models in retrieval-based QA systems.

Findings

Achieved up to 32 percentage points accuracy improvement.

Demonstrated effectiveness across three English datasets.

Outperformed state-of-the-art answer selection models.

Abstract

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.