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

11/05/2020
by   Qianglong Chen, et al.
0

In order to facilitate natural language understanding, the key is to engage commonsense or background knowledge. However, how to engage commonsense effectively in question answering systems is still under exploration in both research academia and industry. In this paper, we propose a novel question-answering method by integrating multiple knowledge sources, i.e. ConceptNet, Wikipedia, and the Cambridge Dictionary, to boost the performance. More concretely, we first introduce a novel graph-based iterative knowledge retrieval module, which iteratively retrieves concepts and entities related to the given question and its choices from multiple knowledge sources. Afterward, we use a pre-trained language model to encode the question, retrieved knowledge and choices, and propose an answer choice-aware attention mechanism to fuse all hidden representations of the previous modules. Finally, the linear classifier for specific tasks is used to predict the answer. Experimental results on the CommonsenseQA dataset show that our method significantly outperforms other competitive methods and achieves the new state-of-the-art. In addition, further ablation studies demonstrate the effectiveness of our graph-based iterative knowledge retrieval module and the answer choice-aware attention module in retrieving and synthesizing background knowledge from multiple knowledge sources.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/09/2019

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

Commonsense question answering aims to answer questions which require ba...
research
09/19/2019

Exploring ways to incorporate additional knowledge to improve Natural Language Commonsense Question Answering

DARPA and Allen AI have proposed a collection of datasets to encourage r...
research
11/26/2020

Automatic Distractor Generation for Multiple Choice Questions in Standard Tests

To assess the knowledge proficiency of a learner, multiple choice questi...
research
11/02/2017

Hi, how can I help you?: Automating enterprise IT support help desks

Question answering is one of the primary challenges of natural language ...
research
03/18/2023

A Graph-Guided Reasoning Approach for Open-ended Commonsense Question Answering

Recently, end-to-end trained models for multiple-choice commonsense ques...
research
07/04/2021

Coarse-to-Careful: Seeking Semantic-related Knowledge for Open-domain Commonsense Question Answering

It is prevalent to utilize external knowledge to help machine answer que...
research
06/08/2017

Dynamic Integration of Background Knowledge in Neural NLU Systems

Common-sense or background knowledge is required to understand natural l...

Please sign up or login with your details

Forgot password? Click here to reset