Question Answering with Texts and Tables Through Deep Reinforcement Learning

• Marcos M. José USP
• Flávio N. Cação Novelo Data
• Maria F. Ribeiro USP
• Rafael M. Cheang USP
• Paulo Pirozelli USP
• Fabio G. Cozman USP

Resumo

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.