Abstract
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. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000393755Publication status
publishedExternal links
Journal / series
arXivPages / Article No.
Publisher
Cornell UniversitySubject
Question answering; Natural Language Processing; Deep LearningOrganisational unit
09462 - Hofmann, Thomas / Hofmann, Thomas
More
Show all metadata
ETH Bibliography
no
Altmetrics