Joint Models for Answer Verification in Question Answering Systems

TL;DR

This paper introduces a joint neural model that enhances answer verification in question answering systems by modeling inter-answer relationships, achieving state-of-the-art results on multiple datasets.

Contribution

It proposes a novel multi-classifier integrated with an answer sentence selection model to better capture inter-answer relations for improved verification.

Findings

Achieved new state-of-the-art in answer sentence selection.

Effective modeling of answer interrelations improves verification accuracy.

Validated on multiple datasets including real-world data.

Abstract

This paper studies joint models for selecting correct answer sentences among the top $k$ provided by answer sentence selection (AS2) modules, which are core components of retrieval-based Question Answering (QA) systems. Our work shows that a critical step to effectively exploit an answer set regards modeling the interrelated information between pair of answers. For this purpose, we build a three-way multi-classifier, which decides if an answer supports, refutes, or is neutral with respect to another one. More specifically, our neural architecture integrates a state-of-the-art AS2 model with the multi-classifier, and a joint layer connecting all components. We tested our models on WikiQA, TREC-QA, and a real-world dataset. The results show that our models obtain the new state of the art in AS2.