End-to-End Open-Domain Question Answering with BERTserini
This addresses the problem of scalable question answering for users needing answers from large text corpora, though it is incremental as it combines existing methods.
The researchers tackled open-domain question answering by integrating BERT with the Anserini IR toolkit to identify answers from Wikipedia articles, reporting large improvements over previous results on a standard benchmark.
We demonstrate an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit. In contrast to most question answering and reading comprehension models today, which operate over small amounts of input text, our system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles in an end-to-end fashion. We report large improvements over previous results on a standard benchmark test collection, showing that fine-tuning pretrained BERT with SQuAD is sufficient to achieve high accuracy in identifying answer spans.