ReQA: An Evaluation for End-to-End Answer Retrieval Models [article]

Amin Ahmad, Noah Constant, Yinfei Yang, Daniel Cer
2019 arXiv   pre-print
Popular QA benchmarks like SQuAD have driven progress on the task of identifying answer spans within a specific passage, with models now surpassing human performance. However, retrieving relevant answers from a huge corpus of documents is still a challenging problem, and places different requirements on the model architecture. There is growing interest in developing scalable answer retrieval models trained end-to-end, bypassing the typical document retrieval step. In this paper, we introduce
more » ... rieval Question-Answering (ReQA), a benchmark for evaluating large-scale sentence-level answer retrieval models. We establish baselines using both neural encoding models as well as classical information retrieval techniques. We release our evaluation code to encourage further work on this challenging task.
arXiv:1907.04780v2 fatcat:vfykkz2lm5bfxoo3awpfnxzrsq