论文标题
重新考虑：使用以跨度为中心的跨注意进行开放域问回答
RECONSIDER: Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answering
论文作者
论文摘要
用于开放域问题答案（QA）的最新机器阅读理解理解（MRC）模型通常使用远距离监督的阳性示例和启发式检索负面示例进行培训。该培训计划可能解释了经验观察，即这些模型在他们的前几个预测中获得了很高的回忆，但总体准确性较低，激发了回答重新排列的需求。我们开发了一种简单有效的重新排列方法（重新考虑），以改善大型预训练的MRC模型的性能。重新考虑从MRC模型的高置信度预测中提取的正面和负面示例进行了培训，并使用通用跨度注释来对较小的候选集合进行以跨度重新排列。结果，Reconsed学会了消除近距离的误报段落，并在四个质量检查任务上实现了新的最新技术，其中包括与真实用户问题的自然问题上的45.5％的精确度，在Triviaqa上有61.7％。
State-of-the-art Machine Reading Comprehension (MRC) models for Open-domain Question Answering (QA) are typically trained for span selection using distantly supervised positive examples and heuristically retrieved negative examples. This training scheme possibly explains empirical observations that these models achieve a high recall amongst their top few predictions, but a low overall accuracy, motivating the need for answer re-ranking. We develop a simple and effective re-ranking approach (RECONSIDER) for span-extraction tasks, that improves upon the performance of large pre-trained MRC models. RECONSIDER is trained on positive and negative examples extracted from high confidence predictions of MRC models, and uses in-passage span annotations to perform span-focused re-ranking over a smaller candidate set. As a result, RECONSIDER learns to eliminate close false positive passages, and achieves a new state of the art on four QA tasks, including 45.5% Exact Match accuracy on Natural Questions with real user questions, and 61.7% on TriviaQA.
