DeepAI AI Chat
Log In Sign Up

Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering

by   Shangwen Lv, et al.
Peking University

Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key challenge is how to obtain evidence from external knowledge and make predictions based on the evidence. Recent works either learn to generate evidence from human-annotated evidence which is expensive to collect, or extract evidence from either structured or unstructured knowledge bases which fails to take advantages of both sources. In this work, we propose to automatically extract evidence from heterogeneous knowledge sources, and answer questions based on the extracted evidence. Specifically, we extract evidence from both structured knowledge base (i.e. ConceptNet) and Wikipedia plain texts. We construct graphs for both sources to obtain the relational structures of evidence. Based on these graphs, we propose a graph-based approach consisting of a graph-based contextual word representation learning module and a graph-based inference module. The first module utilizes graph structural information to re-define the distance between words for learning better contextual word representations. The second module adopts graph convolutional network to encode neighbor information into the representations of nodes, and aggregates evidence with graph attention mechanism for predicting the final answer. Experimental results on CommonsenseQA dataset illustrate that our graph-based approach over both knowledge sources brings improvement over strong baselines. Our approach achieves the state-of-the-art accuracy (75.3 CommonsenseQA leaderboard.


page 1

page 2

page 3

page 4


Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

In order to facilitate natural language understanding, the key is to eng...

KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning

Commonsense reasoning aims to empower machines with the human ability to...

Truth Validation with Evidence

In the modern era, abundant information is easily accessible from variou...

A Heterogeneous Graph with Factual, Temporal and Logical Knowledge for Question Answering Over Dynamic Contexts

We study question answering over a dynamic textual environment. Although...

Focusing Knowledge-based Graph Argument Mining via Topic Modeling

Decision-making usually takes five steps: identifying the problem, colle...

Reasoning Over Semantic-Level Graph for Fact Checking

We study fact-checking in this paper, which aims to verify a textual cla...

KETM:A Knowledge-Enhanced Text Matching method

Text matching is the task of matching two texts and determining the rela...