← Search

Daqian Shi

7 accepted papers

2026

AncientBench: Towards Comprehensive Evaluation on Excavated and Transmitted Chinese Corpora

AAAI 2026technical

Comprehension of ancient texts plays an important role in archaeology and understanding of Chinese history and civilization. The rapid development of large language models needs benchmarks that can evaluate their comprehension of ancient characters. Existing Chinese benchmarks are mostly targeted at

Cited by 0SourcePDFScholar
2026

InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling

AAAI 2026technical

Constructing historical language models (LMs) plays a crucial role in aiding archaeological provenance studies and understanding ancient cultures. However, existing resources present major challenges for training effective LMs on historical texts. First, the scarcity of historical language samples r

Cited by 0SourcePDFScholar
2025

Competitive Distillation: A Simple Learning Strategy for Improving Visual Classification

ICCV 2025poster

Deep Neural Networks (DNNs) have significantly advanced the field of computer vision. To improve DNN training process, knowledge distillation methods demonstrate their effectiveness in accelerating network training by introducing a fixed learning direction from the teacher network to student network…

Cited by 0SourcePDFScholar
2023

FCC: Feature Clusters Compression for Long-Tailed Visual Recognition

CVPR 2023poster

Deep Neural Networks (DNNs) are rather restrictive in long-tailed data, since they commonly exhibit an under-representation for minority classes. Various remedies have been proposed to tackle this problem from different perspectives, but they ignore the impact of the density of Backbone Features (BF…

2023

RZCR: Zero-shot Character Recognition via Radical-based Reasoning

IJCAI 2023poster

The long-tail effect is a common issue that limits the performance of deep learning models on real-world datasets. Character image datasets are also affected by such unbalanced data distribution due to differences in character usage frequency. Thus, current character recognition methods are limited…

Cited by 14SourcePDFScholar
2022

A Simple Contrastive Learning Framework for Interactive Argument Pair Identification via Argument-Context Extraction

EMNLP 2022main

Interactive argument pair identification is an emerging research task for argument mining, aiming to identify whether two arguments are interactively related. It is pointed out that the context of the argument is essential to improve identification performance. However, current context-based methods…

2022

ZiNet: Linking Chinese Characters Spanning Three Thousand Years

ACL 2022findings

Modern Chinese characters evolved from 3,000 years ago. Up to now, tens of thousands of glyphs of ancient characters have been discovered, which must be deciphered by experts to interpret unearthed documents. Experts usually need to compare each ancient character to be examined with similar known on…