Meta Answering for Machine Reading
This work addresses the challenge of enhancing information retrieval in machine reading for applications like question answering, though it is incremental as it builds on existing BERT-based methods.
The paper tackles the problem of improving machine reading by introducing a meta-question answering system that interacts with a black-box environment containing a BERT-based reader, where the meta-answerer selects conditioning information to enhance performance. The result shows that both human and machine meta-answerers outperform the baseline, with the machine version improving precision and recall on the Natural Questions dataset.
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.