b'Haiyang Yu'

research

∙ 09/09/2023

DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions

Multiple object tracking (MOT) tends to become more challenging when sev...

0 Teng Fu, et al. ∙

research

∙ 09/03/2023

Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning

Scene text recognition has been studied for decades due to its broad app...

0 Haiyang Yu, et al. ∙

research

∙ 09/03/2023

Orientation-Independent Chinese Text Recognition in Scene Images

Scene text recognition (STR) has attracted much attention due to its bro...

0 Haiyang Yu, et al. ∙

research

∙ 08/10/2023

A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment

Training large language models (LLMs) with open-domain instruction data ...

0 Yingxiu Zhao, et al. ∙

research

∙ 08/03/2023

Wider and Deeper LLM Networks are Fairer LLM Evaluators

Measuring the quality of responses generated by LLMs is a challenging ta...

0 Xinghua Zhang, et al. ∙

research

∙ 06/30/2023

Preference Ranking Optimization for Human Alignment

Large language models (LLMs) often contain misleading content, emphasizi...

0 Feifan Song, et al. ∙

research

∙ 06/29/2023

Unified Language Representation for Question Answering over Text, Tables, and Images

When trying to answer complex questions, people often rely on multiple s...

0 Bowen Yu, et al. ∙

research

∙ 06/08/2023

Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian

We consider the prediction of the Hamiltonian matrix, which finds use in...

0 Haiyang Yu, et al. ∙

research

∙ 05/18/2023

Causal Document-Grounded Dialogue Pre-training

The goal of document-grounded dialogue (DocGD) is to generate a response...

3 Yingxiu Zhao, et al. ∙

research

∙ 05/09/2023

Privacy-Preserving Collaborative Chinese Text Recognition with Federated Learning

In Chinese text recognition, to compensate for the insufficient local da...

0 Shangchao Su, et al. ∙

research

∙ 04/14/2023

API-Bank: A Benchmark for Tool-Augmented LLMs

Recent research has shown that Large Language Models (LLMs) can utilize ...

0 Minghao Li, et al. ∙

research

∙ 03/20/2023

Weakly-Supervised Text Instance Segmentation

Text segmentation is a challenging vision task with many downstream appl...

0 Xinyan Zu, et al. ∙

research

∙ 03/18/2023

Uncertainty-aware U-Net for Medical Landmark Detection

Heatmap-based methods play an important role in anatomical landmark dete...

0 Ziyang Ye, et al. ∙

research

∙ 02/23/2023

Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs

Multi-document grounded dialogue systems (DGDS) belong to a class of con...

0 Yeqin Zhang, et al. ∙

research

∙ 11/29/2022

Towards Generalized Open Information Extraction

Open Information Extraction (OpenIE) facilitates the open-domain discove...

0 Bowen Yu, et al. ∙

research

∙ 11/24/2022

Chinese Character Recognition with Radical-Structured Stroke Trees

The flourishing blossom of deep learning has witnessed the rapid develop...

0 Haiyang Yu, et al. ∙

research

∙ 11/23/2022

Semi-Supervised Lifelong Language Learning

Lifelong learning aims to accumulate knowledge and alleviate catastrophi...

0 Yingxiu Zhao, et al. ∙

research

∙ 10/20/2022

Doc2Bot: Accessing Heterogeneous Documents via Conversational Bots

This paper introduces Doc2Bot, a novel dataset for building machines tha...

0 Haomin Fu, et al. ∙

research

∙ 10/14/2022

Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue

Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD...

0 Yingxiu Zhao, et al. ∙

research

∙ 07/14/2022

Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration

Building document-grounded dialogue systems have received growing intere...

0 Zhenyu Zhang, et al. ∙

research

∙ 06/15/2022

Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems

We present results from a large-scale experiment on pretraining encoders...

10 Jack FitzGerald, et al. ∙

research

∙ 01/10/2022

DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population

We present a new open-source and extensible knowledge extraction toolkit...

79 Ningyu Zhang, et al. ∙

research

∙ 12/30/2021

Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study

The flourishing blossom of deep learning has witnessed the rapid develop...

14 Jingye Chen, et al. ∙

research

∙ 12/13/2021

Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution

In the last decade, the blossom of deep learning has witnessed the rapid...

0 Jingye Chen, et al. ∙

research

∙ 04/20/2021

Interventional Aspect-Based Sentiment Analysis

Recent neural-based aspect-based sentiment analysis approaches, though a...

0 Zhen Bi, et al. ∙

research

∙ 02/09/2021

On Explainability of Graph Neural Networks via Subgraph Explorations

We consider the problem of explaining the predictions of graph neural ne...

27 Hao Yuan, et al. ∙

research

∙ 12/31/2020

Explainability in Graph Neural Networks: A Taxonomic Survey

Deep learning methods are achieving ever-increasing performance on many ...

227 Hao Yuan, et al. ∙

research

∙ 10/30/2020

Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction

Current supervised relational triple extraction approaches require huge ...

11 Haiyang Yu, et al. ∙

research

∙ 10/11/2020

Mining Truck Platooning Patterns Through Massive Trajectory Data

Truck platooning refers to a series of trucks driving in close proximity...

0 Xiaolei Ma, et al. ∙

research

∙ 09/15/2020

The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis

Long-tailed relation classification is a challenging problem as the head...

0 Haiyang Yu, et al. ∙

research

∙ 09/14/2020

Can Fine-tuning Pre-trained Models Lead to Perfect NLP? A Study of the Generalizability of Relation Extraction

Fine-tuning pre-trained models have achieved impressive performance on s...

0 Ningyu Zhang, et al. ∙

Haiyang Yu

Featured Co-authors