Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs

Abstract

Multi-hop reading comprehension (RC) across documents poses new challenge over singledocument RC because it requires reasoning over multiple documents to reach the final answer. In this paper, we propose a new model to tackle the multi-hop RC problem. We introduce a heterogeneous graph with different types of nodes and edges, which is named as Heterogeneous Document-Entity (HDE) graph. The advantage of HDE graph is that it contains different granularity levels of information including candidates, documents and entities in specific document contexts. Our proposed model can do reasoning over the HDE graph with nodes representation initialized with co-attention and self-attention based context encoders. We employ Graph Neural Networks (GNN) based message passing algorithms to accumulate evidences on the proposed HDE graph. Evaluated on the blind test set of the Qangaroo WIKIHOP data set, our HDE graph based single model delivers competitive result, and the ensemble model achieves the state-of-the-art performance.

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

“…However, EEpath [10] catches all possible entity paths that include many invalid paths and waste computing resources. Also, compared with the models using GNN [22] such as [9], [20], the path can provide better interpretability.…”

“…However, this method would extract many invalid paths, thus bringing in interference and wasting the computing resources. [9], [20], [21] use graph neural networks [22] to obtain the relationship between entities, or add self-attention mechanism [11] into the model, so as to obtain a gain in the result. These three methods provide good interpretability by constructing non-explicit paths or extracting some relevant supporting facts.…”

“…Table 1 presents the results of our proposed multi-hop MRC model on development set of WikiHop, and we compared them with the latest results reported in other original papers. Accuracy (%) Coref-GRU [36] 56.0 Entity-GCN [37] 64.1 CFC [11] 66.4 EEpath [10] 67.1 EPAr [6] 67.2 HDEGraph [9] 68.1 DynSAN [38] 70.1 SCR (proposed) 71.6…”

“…In view of these limitations, this study abandons the current mainstream multi-hop inference methods based on document levels [6]- [8] or entity levels [9], [10]. Rather, it will choose to hop through sentences and gradually build an explicit path based on sentences, so as to deliver the jumps among semantics.…”

How to Represent Paintings: A Painting Classification Using Artistic Comments

“…Recently, graph neural networks have received increasing attention in many applications [ 30 , 31 , 32 , 33 , 34 ]. Kipf and Welling presented a simplified graph neural network model called a graph convolutional network (GCN) [ 35 ].…”