Meta Answering For Machine Reading

Borschinger Benjamin, Boyd-graber Jordan, Buck Christian, Bulian Jannis, Ciaramita Massimiliano, Huebscher Michelle Chen, Gajewski Wojciech, Kilcher Yannic, Nogueira Rodrigo, Saralegu Lierni Sestorain. Arxiv 2019

[Paper]    
Applications BERT Model Architecture Reinforcement Learning Tools Training Techniques

We investigate a framework for machine reading, inspired by real world information-seeking problems, where a meta question answering system interacts with a black box environment. The environment encapsulates a competitive machine reader based on BERT, providing candidate answers to questions, and possibly some context. To validate the realism of our formulation, we ask humans to play the role of a meta-answerer. With just a small snippet of text around an answer, humans can outperform the machine reader, improving recall. Similarly, a simple machine meta-answerer outperforms the environment, improving both precision and recall on the Natural Questions dataset. The system relies on joint training of answer scoring and the selection of conditioning information.

Similar Work