Search Results for author: Mingjun Zhao

Found 11 papers, 5 papers with code

LA3: Efficient Label-Aware AutoAugment

1 code implementation20 Apr 2023 Mingjun Zhao, Shan Lu, Zixuan Wang, Xiaoli Wang, Di Niu

Automated augmentation is an emerging and effective technique to search for data augmentation policies to improve generalizability of deep neural network training.

Bayesian Optimization Data Augmentation

Search-Map-Search: A Frame Selection Paradigm for Action Recognition

no code implementations CVPR 2023 Mingjun Zhao, Yakun Yu, Xiaoli Wang, Lei Yang, Di Niu

To overcome the limitations of existing methods, we propose a Search-Map-Search learning paradigm which combines the advantages of heuristic search and supervised learning to select the best combination of frames from a video as one entity.

Action Recognition Video Understanding

CEIL: A General Classification-Enhanced Iterative Learning Framework for Text Clustering

no code implementations20 Apr 2023 Mingjun Zhao, Mengzhen Wang, Yinglong Ma, Di Niu, Haijiang Wu

To address this issue, we propose CEIL, a novel Classification-Enhanced Iterative Learning framework for short text clustering, which aims at generally promoting the clustering performance by introducing a classification objective to iteratively improve feature representations.

Clustering Deep Clustering +3

GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation

3 code implementations31 Mar 2023 Jian Ma, Mingjun Zhao, Chen Chen, Ruichen Wang, Di Niu, Haonan Lu, Xiaodong Lin

Recent breakthroughs in the field of language-guided image generation have yielded impressive achievements, enabling the creation of high-quality and diverse images based on user instructions. Although the synthesis performance is fascinating, one significant limitation of current image generation models is their insufficient ability to generate text coherently within images, particularly for complex glyph structures like Chinese characters.

Optical Character Recognition (OCR) Text-to-Image Generation

RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation

1 code implementation19 Nov 2021 Chenglin Li, Mingjun Zhao, Huanming Zhang, Chenyun Yu, Lei Cheng, Guoqiang Shu, Beibei Kong, Di Niu

The learned GUR captures the overall preferences and characteristics of a user and thus can be used to augment the behavior data and improve recommendations in any single domain in which the user is involved.

Sequential Recommendation

LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization

1 code implementation Findings (ACL) 2021 Weidong Guo, Mingjun Zhao, Lusheng Zhang, Di Niu, Jinwen Luo, Zhenhua Liu, Zhenyang Li, Jianbo Tang

Language model pre-training based on large corpora has achieved tremendous success in terms of constructing enriched contextual representations and has led to significant performance gains on a diverse range of Natural Language Understanding (NLU) tasks.

Language Modelling Natural Language Understanding

Verdi: Quality Estimation and Error Detection for Bilingual Corpora

1 code implementation31 May 2021 Mingjun Zhao, Haijiang Wu, Di Niu, Zixuan Wang, Xiaoli Wang

Verdi adopts two word predictors to enable diverse features to be extracted from a pair of sentences for subsequent quality estimation, including a transformer-based neural machine translation (NMT) model and a pre-trained cross-lingual language model (XLM).

Language Modelling Machine Translation +3

QBSUM: a Large-Scale Query-Based Document Summarization Dataset from Real-world Applications

no code implementations27 Oct 2020 Mingjun Zhao, ShengLi Yan, Bang Liu, Xinwang Zhong, Qian Hao, Haolan Chen, Di Niu, Bowei Long, Weidong Guo

In this paper, we present QBSUM, a high-quality large-scale dataset consisting of 49, 000+ data samples for the task of Chinese query-based document summarization.

Document Summarization Machine Reading Comprehension

Reinforced Curriculum Learning on Pre-trained Neural Machine Translation Models

no code implementations13 Apr 2020 Mingjun Zhao, Haijiang Wu, Di Niu, Xiaoli Wang

Specifically, we propose a data selection framework based on Deterministic Actor-Critic, in which a critic network predicts the expected change of model performance due to a certain sample, while an actor network learns to select the best sample out of a random batch of samples presented to it.

Machine Translation NMT +1

Learning to Generate Questions by Learning What not to Generate

no code implementations27 Feb 2019 Bang Liu, Mingjun Zhao, Di Niu, Kunfeng Lai, Yancheng He, Haojie Wei, Yu Xu

In CGC-QG, we design a multi-task labeling strategy to identify whether a question word should be copied from the input passage or be generated instead, guiding the model to learn the accurate boundaries between copying and generation.

Multi-Task Learning Question Answering +2

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