[引用][C] Glue: A multi-task benchmark and analysis platform for natural language understanding

A Wang - arXiv preprint arXiv:1804.07461, 2018
被引用次数：7255 相关文章

[引用][C] GLUE: a multi-task benchmark and analysis platform for natural language understanding. CoRR abs/1804.07461 (2018)

A Wang, A Singh, J Michael, F Hill, O Levy… - arXiv preprint arXiv …, 2018
被引用次数：21 相关文章
[PDF] arxiv.org

ASR-GLUE: A new multi-task benchmark for asr-robust natural language understanding

L Feng, J Yu, D Cai, S Liu, H Zheng, Y Wang - arXiv preprint arXiv …, 2021 - arxiv.org
… However, the robustness of natural language understanding (… In this paper, we propose
ASR-GLUE benchmark, a new collection … Based on the proposed benchmark, we systematically …
被引用次数：16 相关文章 所有 2 个版本
[PDF] arxiv.org

Multi-task deep neural networks for natural language understanding

X Liu, P He, W Chen, J Gao - arXiv preprint arXiv:1901.11504, 2019 - arxiv.org
… a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple
natural language understanding (… the NLU tasks defined in the GLUE benchmark as examples. …
被引用次数：1424 相关文章 所有 6 个版本
[PDF] neurips.cc

Superglue: A stickier benchmark for general-purpose language understanding systems

A Wang, Y Pruksachatkun, N Nangia… - … processing …, 2019 - proceedings.neurips.cc
… benchmark styled after GLUE with a new set of more difficult … , we expect that further progress
in multi-task, transfer, and … A unified architecture for natural language processing: Deep …
被引用次数：2201 相关文章 所有 10 个版本
[PDF] arxiv.org

Adversarial glue: A multi-task benchmark for robustness evaluation of language models

B Wang, C Xu, S Wang, Z Gan, Y Cheng, J Gao… - arXiv preprint arXiv …, 2021 - arxiv.org
… across a wide range of natural language understanding (NLU) tasks, … benchmark is still
missing. In this paper, we present Adversarial GLUE (AdvGLUE), a new multi-task benchmark to …
被引用次数：175 相关文章 所有 6 个版本
[PDF] arxiv.org

The microsoft toolkit of multi-task deep neural networks for natural language understanding

X Liu, Y Wang, J Ji, H Cheng, X Zhu, E Awa… - arXiv preprint arXiv …, 2020 - arxiv.org
… -DNN customization for three representative biomedical natural language understanding
tasks: … Glue: A multi-task benchmark and analysis platform for natural language understanding. …
被引用次数：56 相关文章 所有 5 个版本
[PDF] aclanthology.org

Human vs. muppet: A conservative estimate of human performance on the GLUE benchmark

N Nangia, SR Bowman - arXiv preprint arXiv:1905.10425, 2019 - arxiv.org
… 2019b) is a suite of language understanding tasks which has … GLUE is built around nine
sentence-level natural language … because it employs a multi-task learning approach which fine-…
被引用次数：108 相关文章 所有 5 个版本
[PDF] arxiv.org

Multi-task learning for natural language processing in the 2020s: Where are we going?

J Worsham, J Kalita - Pattern Recognition Letters, 2020 - Elsevier
… multi-task learning across all 9 GLUE tasks is the Multi-Task … -depth analysis to the most
recent multi-task benchmarks with … prime research opportunities to understand better the tasks …
被引用次数：89 相关文章 所有 3 个版本
[PDF] ieee.org

Framework for deep learning-based language models using multi-task learning in natural language understanding: A systematic literature review and future directions

RM Samant, MR Bachute, S Gite, K Kotecha - IEEE Access, 2022 - ieeexplore.ieee.org
… Levy, and SR Bowman, "GLUE: A multi-task benchmark and analysis platform for natural
language understanding," arXiv, pp. 1-20, 2018. [81] Alex Wang, et al., SuperGLUE: A Stickier …
被引用次数：73 相关文章 所有 5 个版本