No Answer is Better Than Wrong Answer: A Reflection Model for Document Level Machine Reading Comprehension
arXiv:2009.12056
Abstract
The Natural Questions (NQ) benchmark set brings new challenges to Machine Reading Comprehension: the answers are not only at different levels of granularity (long and short), but also of richer types (including no-answer, yes/no, single-span and multi-span). In this paper, we target at this challenge and handle all answer types systematically. In particular, we propose a novel approach called Reflection Net which leverages a two-step training procedure to identify the no-answer and wrong-answer cases. Extensive experiments are conducted to verify the effectiveness of our approach. At the time of paper writing (May.~20,~2020), our approach achieved the top 1 on both long and short answer leaderboard, with F1 scores of 77.2 and 64.1, respectively.
Accepted by Findings of EMNLP 2020
References in corpus (8)
- Distilling the Knowledge in a Neural Network
- Gaussian Error Linear Units (GELUs)
- Teaching Machines to Read and Comprehend
- Longformer: The Long-Document Transformer
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- Reformer: The Efficient Transformer
- A BERT Baseline for the Natural Questions
- Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering