Natural Language Comprehension with the EpiReader

We present the EpiReader, a novel model for machine comprehension of text. Machine comprehension of unstructured, real-world text is a major research goal for natural language processing. Current tests of machine comprehension pose questions whose answers can be inferred from some supporting text, and evaluate a model's response to the questions. The EpiReader is an end-to-end neural model comprising two components: the first component proposes a small set of candidate answers after comparing a question to its supporting text, and the second component formulates hypotheses using the proposed candidates and the question, then reranks the hypotheses based on their estimated concordance with the supporting text. We present experiments demonstrating that the EpiReader sets a new state-of-the-art on the CNN and Children's Book Test machine comprehension benchmarks, outperforming previous neural models by a significant margin.

PDF Abstract EMNLP 2016 PDF EMNLP 2016 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering Children's Book Test EpiReader Accuracy-CN 67.4% # 8
Accuracy-NE 69.7% # 9
Question Answering CNN / Daily Mail EpiReader CNN 74 # 9


No methods listed for this paper. Add relevant methods here