Question Answering with Texts and Tables through Deep Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning-based architecture for multi-hop question answering that integrates texts and tables, demonstrating competitive F1-score performance on a specialized dataset.

Contribution

It presents a novel reinforcement learning framework to dynamically select tools for multi-hop reasoning over texts and tables in open domain QA.

Findings

Achieved an F1-score of 19.03 on the dataset.

Demonstrated effectiveness of RL in tool selection for multi-hop QA.

Comparable performance to existing iterative systems.

Abstract

This paper proposes a novel architecture to generate multi-hop answers to open domain questions that require information from texts and tables, using the Open Table-and-Text Question Answering dataset for validation and training. One of the most common ways to generate answers in this setting is to retrieve information sequentially, where a selected piece of data helps searching for the next piece. As different models can have distinct behaviors when called in this sequential information search, a challenge is how to select models at each step. Our architecture employs reinforcement learning to choose between different state-of-the-art tools sequentially until, in the end, a desired answer is generated. This system achieved an F1-score of 19.03, comparable to iterative systems in the literature.