Bi-directional Cognitive Thinking Network for Machine Reading Comprehension
This work addresses reading comprehension tasks, offering a novel cognitive-inspired approach that is incremental in nature.
The paper tackles machine reading comprehension by proposing a Bi-directional Cognitive Knowledge Framework (BCKF) that simulates reverse and inertial thinking to answer questions, achieving competitive improvement on the DuReader dataset.
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.