Datasets

Please consider using the systems and benchmarks developed by us

• ArguGPT detector: (2023) ChatGPT英语作文检测器：预测英语议论文由ChatGPT生成的概率（huggingface链接）
• 【new!】ZhoBLiMP: a Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese 包含15种大语言现象、118种小语言现象的汉语最小对立体（minimal pair）；以及20个从头预训练的汉语大模型（参数量：14M to 1.4B）
• MELA：(2024) Multilingual Evaluation of Linguistic Acceptability 多语句法可接受度数据集（10种语言：英、中、俄、意、德、西、日、法、阿、冰岛）
• CoLAC：(2023) Corpus of Linguistic Acceptability in Chinese 汉语句法可接受度数据集
• SwordsmanImp：(2024) A benchmark for pragmatic understanding in Chinese based a sitcom《武林外传》言外之意数据集
• Cured SICK: (2023) Re-annotated SICK dataset; 重新标注的SICK数据集
• ChineseNLIProbing: (2021) Multiple probing datasets for Chinese NLI, including Chinese HANS, expanded diagnostics, etc. 多个汉语自然语言推理评测
• OCNLI： (2020) Original Chinese Natural Language Inference; 原生汉语自然语言推理数据集
• CLUE: (2020) Chinese Language Understanding Evaluation (CLUE) benchmark; 中文语言理解测评基准
• FewCLUE: (2021) Few-shot CLUE Benchmark; CLUE少样本学习评测

NAtural LOgic Meets MAchine Learning (NALOMA) workshop

Workshop at WESSLLI 2020-2023. webpage