arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.14103cs.CLcs.AI
收藏

区分性阅读理解的Lite统一模型

Lite Unified Modeling for Discriminative Reading Comprehension

Shanghai Jiao Tong University(上海交通大学);Leyan Tech(乐言科技)

Yilin Zhao, Hai Zhao, Libin Shen, Yinggong Zhao

摘要:

作为机器阅读理解的一个主要范畴,判别式机器阅读理解的目标是从给定的材料中预测答案。然而,各种判别式MRC任务的重点可能是不同的:多选择MRC需要模型突出并整合所有潜在的关键证据全局;而提取MRC则侧重于更高的局部边界精确度以进行答案提取。在以往的工作中,缺乏一个统一的设计与针对性的整体判别MRC任务。为了填补上述空白,我们提出了一个轻量级的POS-Enhanced Iterative Co-Attention Network(POI-Net)作为统一建模的第一次尝试,有针对性地同步处理不同的歧视性MRC任务。几乎没有引入更多的参数,我们的精简统一设计带来了编码器和解码器组件的模型显着改善。四个判别MRC基准的评估结果一致表明我们的模型的一般有效性和适用性,代码可在https://github.com/Yilin1111/poi-net。

英文摘要:

As a broad and major category in machine reading comprehension (MRC), the generalized goal of discriminative MRC is answer prediction from the given materials. However, the focuses of various discriminative MRC tasks may be diverse enough: multi-choice MRC requires model to highlight and integrate all potential critical evidence globally; while extractive MRC focuses on higher local boundary preciseness for answer extraction. Among previous works, there lacks a unified design with pertinence for the overall discriminative MRC tasks. To fill in above gap, we propose a lightweight POS-Enhanced Iterative Co-Attention Network (POI-Net) as the first attempt of unified modeling with pertinence, to handle diverse discriminative MRC tasks synchronously. Nearly without introducing more parameters, our lite unified design brings model significant improvement with both encoder and decoder components. The evaluation results on four discriminative MRC benchmarks consistently indicate the general effectiveness and applicability of our model, and the code is available at https://github.com/Yilin1111/poi-net.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑