Picture for Baotian Hu

Baotian Hu

A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues

May 08, 2023
Yunxin Li, Baotian Hu, Xinyu Chen, Yuxin Ding, Lin Ma, Min Zhang

Figure 1 for A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues

Figure 2 for A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues

Figure 3 for A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues

Figure 4 for A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues

* Accepted to ACL 2023 Main Conference

Access Paper or Ask Questions

A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text

May 05, 2023
Yunxin Li, Baotian Hu, Yuxin Ding, Lin Ma, Min Zhang

Figure 1 for A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text

Figure 2 for A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text

Figure 3 for A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text

Figure 4 for A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text

* Accepted to ACL 2023 Main Conference

Access Paper or Ask Questions

LMEye: An Interactive Perception Network for Large Language Models

May 05, 2023
Yunxin Li, Baotian Hu, Xinyu Chen, Lin Ma, Min Zhang

Figure 1 for LMEye: An Interactive Perception Network for Large Language Models

Figure 2 for LMEye: An Interactive Perception Network for Large Language Models

Figure 3 for LMEye: An Interactive Perception Network for Large Language Models

Figure 4 for LMEye: An Interactive Perception Network for Large Language Models

* working in progress

Access Paper or Ask Questions

Prompt-based Text Entailment for Low-Resource Named Entity Recognition

Nov 06, 2022
Dongfang Li, Baotian Hu, Qingcai Chen

Figure 1 for Prompt-based Text Entailment for Low-Resource Named Entity Recognition

Figure 2 for Prompt-based Text Entailment for Low-Resource Named Entity Recognition

Figure 3 for Prompt-based Text Entailment for Low-Resource Named Entity Recognition

Figure 4 for Prompt-based Text Entailment for Low-Resource Named Entity Recognition

* COLING 2022

Access Paper or Ask Questions

An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks

Oct 30, 2022
Yuxiang Wu, Yu Zhao, Baotian Hu, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel

Figure 1 for An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks

Figure 2 for An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks

Figure 3 for An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks

Figure 4 for An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks

* EMNLP 2022 main conference long paper. 8 pages, 6 figures

Access Paper or Ask Questions

Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark

Jul 26, 2022
Zhenran Xu, Zifei Shan, Yuxin Li, Baotian Hu, Bing Qin

Figure 1 for Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark

Figure 2 for Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark

Figure 3 for Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark

Figure 4 for Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark

* 19 pages, 3 figures, 12 tables. Dataset available at https://github.com/imryanxu/Hansel

Access Paper or Ask Questions

Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations

Jul 23, 2022
Qian Yang, Yunxin Li, Baotian Hu, Lin Ma, Yuxing Ding, Min Zhang

Figure 1 for Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations

Figure 2 for Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations

Figure 3 for Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations

Figure 4 for Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations

* 11 pages (including Supplementary Materials); Accepted to ACM MM 2022

Access Paper or Ask Questions