Abstract

To bridge the gap between Machine Reading Comprehension (MRC) models and human beings, which is mainly reflected in the hunger for data and the robustness to noise, in this paper, we explore how to integrate the neural networks of MRC models with the general knowledge of human beings. On the one hand, we propose a data enrichment method, which uses WordNet to extract inter-word semantic connections as general knowledge from each given passage-question pair. On the other hand, we propose an end-to-end MRC model named as Knowledge Aided Reader (KAR), which explicitly uses the above extracted general knowledge to assist its attention mechanisms. Based on the data enrichment method, KAR is comparable in performance with the state-of-the-art MRC models, and significantly more robust to noise than them. When only a subset (20%-80%) of the training examples are available, KAR outperforms the state-of-the-art MRC models by a large margin, and is still reasonably robust to noise.

Highlights

  • Machine Reading Comprehension (MRC), as the name suggests, requires a machine to read a passage and answer its relevant questions

  • We propose a data enrichment method, which uses WordNet to extract inter-word semantic connections as general knowledge from each given passage-question pair

  • We propose an end-to-end MRC model named as Knowledge Aided Reader (KAR), which explicitly uses the above extracted general knowledge to assist its attention mechanisms

Read more

Summary

Introduction

Machine Reading Comprehension (MRC), as the name suggests, requires a machine to read a passage and answer its relevant questions. On the other hand, Jia and Liang (2017) revealed that intentionally injected noise (e.g. misleading sentences) in evaluation examples causes the performance of MRC models to drop significantly, while human beings are far less likely to suffer from this The reason for these phenomena, we believe, is that MRC models can only utilize the knowledge contained in each given passagequestion pair, but in addition to this, human beings can utilize general knowledge. A promising strategy to bridge the gap mentioned above is to integrate the neural networks of MRC models with the general knowledge of human beings To this end, it is necessary to solve two problems: extracting general knowledge from passagequestion pairs and utilizing the extracted general knowledge in the prediction of answer spans. A broad variety of knowledge bases are available, such as WordNet (Fellbaum, 1998) storing semantic knowledge, ConceptNet (Speer et al, 2017) storing commonsense knowledge, and Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2263–2272 Florence, Italy, July 28 - August 2, 2019. c 2019 Association for Computational Linguistics

Objectives
Methods
Findings
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call