A Sentence-Based Circular Reasoning Model in Multi-Hop Reading Comprehension

Lijun Huo,Xiang Zhao

doi:10.1109/access.2020.3025957

Abstract

Multi-hop Machine Reading Comprehension (MRC) requires models to mine and utilize relevant information from multiple documents to predict the answer to a semantics-related query. The existing researches resort to either document-level or entity-level inferences among relevant information, but such practices may be too coarse or too subtle to result less accurate understanding of the text. To address this issue, this research proposes a Sentence-based Circular Reasoning (SCR) approach, which starts with sentence representation and then unites the query to establish a reasoning path based on a loop inference unit. Further, the model synthesizes the information existing in the reasoning path and receives a probability distribution for selecting the correct answer. In addition, this study proposes a nested mechanism to extend the probability distribution for weighting. And it is proven that this mechanism can assist the model to perform better. Some experiments evaluate SCR on two popular multi-hop MRC benchmark datasets, WikiHop and MedHop, achieving 71.6 and 63.2 in terms of accuracy, respectively, and thus exhibiting competitive results compared with the state-of-the-art model. Additionally, qualitative analyses also demonstrate the validity and interpretability of SCR.

Highlights

As an important technique in the field of Natural Language Processing (NLP), machine reading comprehension can measure how well machines understand complex text
If the path uses sentences as nodes, it has obvious logic and less information redundancy, delivering great assistance to acquiring answers, and explaining the reasoning process well. Taking these requirements into account, this study proposes a Sentence-based Circular Reasoning model, named SCR, which uses sentence inference to construct an information path and consists of three modules: Sentence Encoder (SE), Path Generator (PG) and Path Evaluator (PE)
In this paper, we propose a multi-hop Machine Reading Comprehension (MRC) model based on sentence reasoning, named SCR, in which sentences play a pivotal role in constructing an information path

Summary

INTRODUCTION

As an important technique in the field of Natural Language Processing (NLP), machine reading comprehension can measure how well machines understand complex text. If the path uses sentences as nodes, it has obvious logic and less information redundancy, delivering great assistance to acquiring answers, and explaining the reasoning process well Taking these requirements into account, this study proposes a Sentence-based Circular Reasoning model, named SCR, which uses sentence inference to construct an information path and consists of three modules: Sentence Encoder (SE), Path Generator (PG) and Path Evaluator (PE). It proposes to leverage sentence-based reasoning for multi-hop MRC, which builds an information path that can assist the model to accomplish the task. This research focuses on the multi-choice task and utilizes WikiHop and MedHop [15] datasets, while adopting sentence-based reasoning to construct a precise inference path It proposes and applies the NM to optimize the sentence representation as well as expressions of some other modules.

RELATED WORK

PATH EVALUATOR

EXPERIMENT

EXPERIMENTAL SETTINGS

Findings

CONCLUSION