Bi-directional Cognitive Thinking Network for Machine Reading Comprehension
arXiv:2010.10286
Abstract
We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory. It aims to simulate two ways of thinking in the brain to answer questions, including reverse thinking and inertial thinking. To validate the effectiveness of our framework, we design a corresponding Bi-directional Cognitive Thinking Network (BCTN) to encode the passage and generate a question (answer) given an answer (question) and decouple the bi-directional knowledge. The model has the ability to reverse reasoning questions which can assist inertial thinking to generate more accurate answers. Competitive improvement is observed in DuReader dataset, confirming our hypothesis that bi-directional knowledge helps the QA task. The novel framework shows an interesting perspective on machine reading comprehension and cognitive science.
arXiv commentAccepted to COLING 2020
References in corpus (7)
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- Bidirectional Attention Flow for Machine Comprehension
- Dynamic Coattention Networks For Question Answering
- Machine Comprehension Using Match-LSTM and Answer Pointer
- A Joint Model for Question Answering and Question Generation
- S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
- Modeling reverse thinking for machine learning