paper-with-me

Papers

Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention

2021-12-06 · Yichong Xu, Chenguang Zhu, Shuohang Wang, Siqi Sun, Hao Cheng, Xiaodong Liu, Jianfeng Gao, Pengcheng He, Michael Zeng, Xuedong Huang

Most of today's AI systems focus on using self-attention mechanisms and transformer architectures on large amounts of diverse data to achieve impressive performance gains. In this paper, we propose to augment the transformer architecture with an external attention mechanism to bring external knowledge and context to bear. By integrating external information into the prediction process, we hope to reduce the need for ever-larger models and increase the democratization of AI systems. We find that the proposed external attention mechanism can significantly improve the performance of existing AI systems, allowing practitioners to easily customize foundation AI models to many diverse downstream applications. In particular, we focus on the task of Commonsense Reasoning, demonstrating that the proposed external attention mechanism can augment existing transformer models and significantly improve the model's reasoning capabilities. The proposed system, Knowledgeable External Attention for commonsense Reasoning (KEAR), reaches human parity on the open CommonsenseQA research benchmark with an accuracy of 89.4\% in comparison to the human accuracy of 88.9\%.

📄 PDF Abstract BibTeX arXiv:2112.03254

Code (2)

microsoft/kear 공식 구현 pytorch
microsoft/DEKCOR-CommonsenseQA pytorch

Tasks

Common Sense Reasoning

Similar Papers 제목 키워드 기반

CommonsenseQA 2.0: Exposing the Limits of AI through Gamification

2022-01-14 · Alon Talmor, Ori Yoran, Ronan Le Bras, Chandra Bhagavatula 외

Constructing benchmarks that test the abilities of modern natural language understanding models is difficult - pre-trained language models exploit artifacts in benchmarks to achieve human parity, but still fail on advers…

Common Sense ReasoningNatural Language Understanding

BroadWay: Boost Your Text-to-Video Generation Model in a Training-free Way

2024-10-08 · Jiazi Bu, Pengyang Ling, Pan Zhang, Tong Wu 외

The text-to-video (T2V) generation models, offering convenient visual creation, have recently garnered increasing attention. Despite their substantial potential, the generated videos may present artifacts, including stru…

DecoderText-to-Video GenerationVideo Generation

ByTheWay: Boost Your Text-to-Video Generation Model to Higher Quality in a Training-free Way

2025-01-01 · CVPR 2025 1 · Jiazi Bu, Pengyang Ling, Pan Zhang, Tong Wu 외

The text-to-video (T2V) generation models, offering convenient visual creation, have recently garnered increasing attention. Despite their substantial potential, the generated videos may present artifacts, including …

Text-to-Video GenerationVideo Generation

Lower bounds for one-layer transformers that compute parity

2026-05-12 · Daniel Hsu arxiv

This note shows that no self-attention layer post-processed by a rational function can sign-represent the parity function unless the product of the number of heads and the degree of the post-processing function grows lin…

Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume

2020-03-31 · CVPR 2020 6 · Adrian Johnston, Gustavo Carneiro

Monocular depth estimation has become one of the most studied applications in computer vision, where the most accurate approaches are based on fully supervised learning models. However, the acquisition of accurate and la…

Depth EstimationMonocular Depth Estimation