Výsledky vyhledávání - "Zhang, Jingshen"

Report

Label Confidence Weighted Learning for Target-level Sentence Simplification

Multi-level sentence simplification generates simplified sentences with varying language proficiency levels. We propose Label Confidence Weighted Learning (LCWL), a novel approach that incorporates a label confidence weighting scheme in the training

Externí odkaz: http://arxiv.org/abs/2410.05748

Zobrazit plný text záznamu

Report

System Report for CCL24-Eval Task 7: Multi-Error Modeling and Fluency-Targeted Pre-training for Chinese Essay Evaluation

Autor: Zhang, Jingshen, Yang, Xiangyu, Su, Xinkai, Chen, Xinglu, Huang, Tianyou, Qiu, Xinying

This system report presents our approaches and results for the Chinese Essay Fluency Evaluation (CEFE) task at CCL-2024. For Track 1, we optimized predictions for challenging fine-grained error types using binary classification models and trained coa

Externí odkaz: http://arxiv.org/abs/2407.08206

Zobrazit plný text záznamu

Report

Cross-Lingual Word Alignment for ASEAN Languages with Contrastive Learning

Autor: Zhang, Jingshen, Qiu, Xinying, Shen, Teng, Wang, Wenyu, Zhang, Kailin, Feng, Wenhe

Cross-lingual word alignment plays a crucial role in various natural language processing tasks, particularly for low-resource languages. Recent study proposes a BiLSTM-based encoder-decoder model that outperforms pre-trained language models in low-re

Externí odkaz: http://arxiv.org/abs/2407.05054

Zobrazit plný text záznamu

Report

Readability-guided Idiom-aware Sentence Simplification (RISS) for Chinese

Autor: Zhang, Jingshen, Chen, Xinglu, Qiu, Xinying, Wang, Zhimin, Feng, Wenhe

Chinese sentence simplification faces challenges due to the lack of large-scale labeled parallel corpora and the prevalence of idioms. To address these challenges, we propose Readability-guided Idiom-aware Sentence Simplification (RISS), a novel fram

Externí odkaz: http://arxiv.org/abs/2406.02974

Zobrazit plný text záznamu

Report

Controlling Cloze-test Question Item Difficulty with PLM-based Surrogate Models for IRT Assessment

Autor: Zhang, Jingshen, Xie, Jiajun, Qiu, Xinying

Item difficulty plays a crucial role in adaptive testing. However, few works have focused on generating questions of varying difficulty levels, especially for multiple-choice (MC) cloze tests. We propose training pre-trained language models (PLMs) as

Externí odkaz: http://arxiv.org/abs/2403.01456

Zobrazit plný text záznamu