论文标题
混音：一种多任务学习方法来解决开放域问题回答
MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering
论文作者
论文摘要
本文介绍了Mix，这是一种多任务深度学习方法，以解决开放式的问题索问题。首先，我们将系统设计为3个构建块的多阶段管道：一个基于BM25的回收器，可减少搜索空间，基于罗伯塔的得分手，以及分别排名的段落检索段落和提取相关文本跨度的提取器。最终，我们进一步提高了系统的计算效率来应对可伸缩性挑战：多亏了多任务学习，我们将得分手和提取器解决的近距离任务并行。我们的系统与在小队开放的基准测试中的最先进的表演相提并论，同时在概念上更简单。
This paper introduces MIX, a multi-task deep learning approach to solve open-ended question-answering. First, we design our system as a multi-stage pipeline of 3 building blocks: a BM25-based Retriever to reduce the search space, a RoBERTa-based Scorer, and an Extractor to rank retrieved paragraphs and extract relevant text spans, respectively. Eventually, we further improve the computational efficiency of our system to deal with the scalability challenge: thanks to multi-task learning, we parallelize the close tasks solved by the Scorer and the Extractor. Our system is on par with state-of-the-art performances on the squad-open benchmark while being simpler conceptually.
