A Simple Approach to Jointly Rank Passages and Select Relevant Sentences in the OBQA Context

TL;DR

This paper introduces a simple, joint framework for passage ranking and sentence selection in open book QA, leveraging task interaction to improve performance on HotpotQA.

Contribution

The work proposes a unified model with consistency and similarity constraints for joint passage and sentence selection, outperforming baselines.

Findings

Achieves 28% improvement in sentence exact match on HotpotQA.

Outperforms previous systems with a simpler framework.

Demonstrates the benefit of joint training for passage and sentence tasks.

Abstract

In the open book question answering (OBQA) task, selecting the relevant passages and sentences from distracting information is crucial to reason the answer to a question. HotpotQA dataset is designed to teach and evaluate systems to do both passage ranking and sentence selection. Many existing frameworks use separate models to select relevant passages and sentences respectively. Such systems not only have high complexity in terms of the parameters of models but also fail to take the advantage of training these two tasks together since one task can be beneficial for the other one. In this work, we present a simple yet effective framework to address these limitations by jointly ranking passages and selecting sentences. Furthermore, we propose consistency and similarity constraints to promote the correlation and interaction between passage ranking and sentence selection.The experiments demonstrate that our framework can achieve competitive results with previous systems and outperform the baseline by 28\% in terms of exact matching of relevant sentences on the HotpotQA dataset.