Search Results for author: Can Ma

Found 13 papers, 5 papers with code

Resolving Sentiment Discrepancy for Multimodal Sentiment Detection via Semantics Completion and Decomposition

no code implementations9 Jul 2024 Daiqing Wu, Dongbao Yang, Huawen Shen, Can Ma, Yu Zhou

In the semantics completion module, we complement image and text representations with the semantics of the OCR text embedded in the image, helping bridge the sentiment gap.

Contrastive Learning Optical Character Recognition (OCR)

Distilling Mathematical Reasoning Capabilities into Small Language Models

no code implementations22 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.

Mathematical Reasoning

Unifying Structured Data as Graph for Data-to-Text Pre-Training

1 code implementation2 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.

Data-to-Text Generation

Separate and Locate: Rethink the Text in Text-based Visual Question Answering

1 code implementation31 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.

Optical Character Recognition (OCR) Position +3

A Survey on Model Compression for Large Language Models

no code implementations15 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.

Benchmarking Knowledge Distillation +2

CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality

no code implementations20 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.

Plan-then-Seam: Towards Efficient Table-to-Text Generation

1 code implementation10 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.

Table-to-Text Generation

Learning Better Representation for Tables by Self-Supervised Tasks

no code implementations15 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.

Table-to-Text Generation

Two-Level Residual Distillation based Triple Network for Incremental Object Detection

no code implementations27 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.

Incremental Learning Object +3

Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning

1 code implementation2 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.

Representation Learning Retrieval +4

Cannot find the paper you are looking for? You can Submit a new open access paper.