no code implementations • 22 Jan 2024 • Xunyu Zhu, Jian Li, Yong liu, Can Ma, Weiping Wang
This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance.
1 code implementation • 2 Jan 2024 • Shujie Li, Liang Li, Ruiying Geng, Min Yang, Binhua Li, Guanghu Yuan, Wanwei He, Shao Yuan, Can Ma, Fei Huang, Yongbin Li
In this paper, we unify different types of structured data (i. e., table, key-value data, knowledge graph) into the graph format and cast different data-to-text generation tasks as graph-to-text generation.
1 code implementation • 31 Aug 2023 • Chengyang Fang, Jiangnan Li, Liang Li, Can Ma, Dayong Hu
To tackle these problems, we propose a novel method named Separate and Locate (SaL) that explores text contextual cues and designs spatial position embedding to construct spatial relations between OCR texts.
no code implementations • 15 Aug 2023 • Xunyu Zhu, Jian Li, Yong liu, Can Ma, Weiping Wang
As these challenges become increasingly pertinent, the field of model compression has emerged as a pivotal research area to alleviate these limitations.
no code implementations • 20 Jun 2023 • Liang Li, Ruiying Geng, Chengyang Fang, Bing Li, Can Ma, Rongyu Cao, Binhua Li, Fei Huang, Yongbin Li
To alleviate these limitations, in this paper, we present CATS, a pragmatic Chinese answer-to-sequence dataset with large scale and high quality.
1 code implementation • 10 Feb 2023 • Liang Li, Ruiying Geng, Chengyang Fang, Bing Li, Can Ma, Binhua Li, Yongbin Li
Table-to-text generation aims at automatically generating text to help people conveniently obtain salient information in tables.
no code implementations • COLING 2022 • Liang Li, Ruiying Geng, Bowen Li, Can Ma, Yinliang Yue, Binhua Li, Yongbin Li
Most graph-to-text works are built on the encoder-decoder framework with cross-attention mechanism.
no code implementations • 24 Mar 2022 • Chengyang Fang, Gangyan Zeng, Yu Zhou, Daiqing Wu, Can Ma, Dayong Hu, Weiping Wang
Texts in scene images convey critical information for scene understanding and reasoning.
Optical Character Recognition Optical Character Recognition (OCR) +3
1 code implementation • ACL 2021 • Liang Li, Can Ma, Yinliang Yue, Dayong Hu
However, it is hard for a vanilla encoder to capture these.
Ranked #1 on Table-to-Text Generation on RotoWire
no code implementations • 15 Oct 2020 • Liang Li, Can Ma, Yinliang Yue, Linjun Shou, Dayong Hu
Secondly, the target texts in training dataset may contain redundant information or facts do not exist in the input tables.
no code implementations • 27 Jul 2020 • Dongbao Yang, Yu Zhou, Dayan Wu, Can Ma, Fei Yang, Weiping Wang
Modern object detection methods based on convolutional neural network suffer from severe catastrophic forgetting in learning new classes without original data.
1 code implementation • 2 Jan 2020 • Dezhao Luo, Chang Liu, Yu Zhou, Dongbao Yang, Can Ma, Qixiang Ye, Weiping Wang
As a proxy task, it converts rich self-supervised representations into video clip operations (options), which enhances the flexibility and reduces the complexity of representation learning.
Ranked #11 on Self-supervised Video Retrieval on HMDB51