论文标题
地图：一种基于矩阵的预测方法，用于改善机器阅读理解中的跨度提取
MaP: A Matrix-based Prediction Approach to Improve Span Extraction in Machine Reading Comprehension
论文作者
论文摘要
跨度提取是机器阅读理解的重要问题。大多数现有算法通过生成两个概率向量来预测在给定相应上下文中答案跨度的开始和结束位置。在本文中，我们提出了一种新型方法，该方法将概率向量扩展到概率矩阵。这样的矩阵可以涵盖更多的起始位置对。确切地说，对于每个可能的启动索引，该方法始终生成一个最终概率向量。此外，我们提出了一种基于抽样的培训策略，以解决矩阵培训阶段的计算成本和内存问题。我们评估了我们的1.1小队和其他三个问题的方法。将最具竞争力的模型Bert和Bidaf作为骨干，我们提出的方法可以在所有数据集中获得一致的改进，这证明了该方法的有效性。
Span extraction is an essential problem in machine reading comprehension. Most of the existing algorithms predict the start and end positions of an answer span in the given corresponding context by generating two probability vectors. In this paper, we propose a novel approach that extends the probability vector to a probability matrix. Such a matrix can cover more start-end position pairs. Precisely, to each possible start index, the method always generates an end probability vector. Besides, we propose a sampling-based training strategy to address the computational cost and memory issue in the matrix training phase. We evaluate our method on SQuAD 1.1 and three other question answering benchmarks. Leveraging the most competitive models BERT and BiDAF as the backbone, our proposed approach can get consistent improvements in all datasets, demonstrating the effectiveness of the proposed method.
