Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering

ICLR 2019 Victor Zhong • Caiming Xiong • Nitish Shirish Keskar • Richard Socher

End-to-end neural models have made significant progress in question answering, however recent studies show that these models implicitly assume that the answer and evidence appear close together in a single document. In this work, we propose the Coarse-grain Fine-grain Coattention Network (CFC), a new question answering model that combines information from evidence across multiple documents. The CFC consists of a coarse-grain module that interprets documents with respect to the query then finds a relevant answer, and a fine-grain module which scores each candidate answer by comparing its occurrences across all of the documents with the query.

Full paper

Evaluation


Task Dataset Model Metric name Metric value Global rank Compare
Question Answering WikiHop CFC Test 70.6 # 1