Výsledky vyhledávání

Report

MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators

Autor: Lu, Qingyu, Ding, Liang, Zhang, Kanjian, Zhang, Jinxia, Tao, Dacheng

Large Language Models (LLMs) have shown significant potential as judges for Machine Translation (MT) quality assessment, providing both scores and fine-grained feedback. Although approaches such as GEMBA-MQM has shown SOTA performance on reference-fr

Externí odkaz: http://arxiv.org/abs/2409.14335

Zobrazit plný text záznamu

Report

Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models

Autor: Lu, Qingyu, Qiu, Baopu, Ding, Liang, Zhang, Kanjian, Kocmi, Tom, Tao, Dacheng

Generative large language models (LLMs), e.g., ChatGPT, have demonstrated remarkable proficiency across several NLP tasks, such as machine translation, text summarization. Recent research (Kocmi and Federmann, 2023) has shown that utilizing LLMs for

Externí odkaz: http://arxiv.org/abs/2303.13809

Zobrazit plný text záznamu

Report

Toward Human-Like Evaluation for Natural Language Generation with Error Analysis

Autor: Lu, Qingyu, Ding, Liang, Xie, Liping, Zhang, Kanjian, Wong, Derek F., Tao, Dacheng

The state-of-the-art language model-based automatic metrics, e.g. BARTScore, benefiting from large-scale contextualized pre-training, have been successfully used in a wide range of natural language generation (NLG) tasks, including machine translatio

Externí odkaz: http://arxiv.org/abs/2212.10179

Zobrazit plný text záznamu

Report

Vega-MT: The JD Explore Academy Translation System for WMT22

Autor: Zan, Changtong, Peng, Keqin, Ding, Liang, Qiu, Baopu, Liu, Boan, He, Shwai, Lu, Qingyu, Zhang, Zheng, Liu, Chuang, Liu, Weifeng, Zhan, Yibing, Tao, Dacheng

We describe the JD Explore Academy's submission of the WMT 2022 shared general translation task. We participated in all high-resource tracks and one medium-resource track, including Chinese-English, German-English, Czech-English, Russian-English, and

Externí odkaz: http://arxiv.org/abs/2209.09444

Zobrazit plný text záznamu