Asking Complex Questions with Multi-hop Answer-focused Reasoning

TL;DR

This paper introduces a new multi-hop question generation task that creates complex, semantically relevant questions by modeling multiple entities and their relations across documents, advancing beyond simple single-hop questions.

Contribution

It proposes a novel multi-hop answer-focused reasoning model on an entity graph to generate complex questions, serving as a baseline for future research.

Findings

Outperforms existing models on HOTPOTQA dataset

Effectively models multi-entity semantic relations

Establishes a new baseline for multi-hop question generation

Abstract

Asking questions from natural language text has attracted increasing attention recently, and several schemes have been proposed with promising results by asking the right question words and copy relevant words from the input to the question. However, most state-of-the-art methods focus on asking simple questions involving single-hop relations. In this paper, we propose a new task called multihop question generation that asks complex and semantically relevant questions by additionally discovering and modeling the multiple entities and their semantic relations given a collection of documents and the corresponding answer 1. To solve the problem, we propose multi-hop answer-focused reasoning on the grounded answer-centric entity graph to include different granularity levels of semantic information including the word-level and document-level semantics of the entities and their semantic relations. Through extensive experiments on the HOTPOTQA dataset, we demonstrate the superiority and effectiveness of our proposed model that serves as a baseline to motivate future work.