Numerical reasoning in machine reading comprehension tasks: are we there yet?
Numerical reasoning in machine reading comprehension tasks: are we there yet?
复制标题
机器阅读理解任务中的数值推理：我们到了吗？
DOI：
10.18653/v1/2021.emnlp-main.759
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
A. Russo
中科院分区：
文献类型：
--
作者：
Hadeel Al;P. Madhyastha;A. Russo
基于数字推理的机器阅读理解是一个任务，涉及阅读理解沿着使用算术运算，如加，减，排序和计数。DROP基准（Dua等人，2019）是最近的一个数据集，它启发了旨在解决这一任务的NLP模型的设计。这些模型目前在DROP排行榜上的排名超过了标准指标，表明这些模型已经达到了接近人类的性能。然而，这是否意味着这些模型已经学会了推理？在本文中，我们提出了一个控制研究的一些最高性能的模型架构的任务的数值推理。我们的观察表明，标准指标无法衡量这些任务的进展情况。
Numerical reasoning based machine reading comprehension is a task that involves reading comprehension along with using arithmetic operations such as addition, subtraction, sorting and counting. The DROP benchmark (Dua et al., 2019) is a recent dataset that has inspired the design of NLP models aimed at solving this task. The current standings of these models in the DROP leaderboard, over standard metrics, suggests that the models have achieved near-human performance. However, does this mean that these models have learned to reason? In this paper, we present a controlled study on some of the top-performing model architectures for the task of numerical reasoning. Our observations suggest that the standard metrics are incapable of measuring progress towards such tasks.
DOI：
10.18653/v1/2020.findings-emnlp.117
发表时间：
2020-04
期刊：
--
影响因子：
--
作者：
Matt Gardner;Yoav Artzi;Jonathan Berant;Ben Bogin;Sihao Chen;Dheeru Dua;Yanai Elazar;Ananth Gottumukkala;Nitish Gupta;Hannaneh Hajishirzi;Gabriel Ilharco;Daniel Khashabi;Kevin Lin;Jiangming Liu;Nelson F. Liu;Phoebe Mulcaire;Qiang Ning;Sameer Singh;Noah A. Smith;Sanjay Subramanian;Eric Wallace;Ally Zhang;Ben Zhou
通讯作者：
Matt Gardner;Yoav Artzi;Jonathan Berant;Ben Bogin;Sihao Chen;Dheeru Dua;Yanai Elazar;Ananth Gottumukkala;Nitish Gupta;Hannaneh Hajishirzi;Gabriel Ilharco;Daniel Khashabi;Kevin Lin;Jiangming Liu;Nelson F. Liu;Phoebe Mulcaire;Qiang Ning;Sameer Singh;Noah A. Smith;Sanjay Subramanian;Eric Wallace;Ally Zhang;Ben Zhou