Filters








2,867 Hits in 3.9 sec

CLUE: A Chinese Language Understanding Evaluation Benchmark [article]

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong (+20 others)
2020 arXiv   pre-print
To help remedy this issue, we introduce the first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark.  ...  The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks.  ...  We are also grateful to the annotators and engineers who have spent much of their time and effort helping with the creation of the CLUE benchmark.  ... 
arXiv:2004.05986v3 fatcat:xwmawjovnzcsjjvucr6ngiiauy

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark [article]

Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni (+11 others)
2022 arXiv   pre-print
To facilitate research in this direction, we collect real-world biomedical data and present the first Chinese Biomedical Language Understanding Evaluation (CBLUE) benchmark: a collection of natural language  ...  With the development of biomedical language understanding benchmarks, AI applications are widely used in the medical field.  ...  A significant trend is the emergence of multi-task leaderboards, such as GLUE (General Language Understanding Evaluation) and CLUE (Chinese Language Understanding Evaluation).  ... 
arXiv:2106.08087v6 fatcat:q4ppng5735ezbjaqv3wtukdrsy

CLUE: A Chinese Language Understanding Evaluation Benchmark

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong (+20 others)
2020 Proceedings of the 28th International Conference on Computational Linguistics   unpublished
To help remedy this issue, we introduce the first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark.  ...  The advent of natural language understanding (NLU) benchmarks for English, such as GLUE and SuperGLUE allows new NLU models to be evaluated across a diverse set of tasks.  ...  We are also grateful to the annotators and engineers who have spent much of their time and effort helping with the creation of the CLUE benchmark.  ... 
doi:10.18653/v1/2020.coling-main.419 fatcat:p5snbrr2sjd6rkl3f4jworczfq

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark

Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni (+11 others)
2022 Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   unpublished
To facilitate research in this direction, we collect real-world biomedical data and present the first Chinese Biomedical Language Understanding Evaluation (CBLUE) benchmark: a collection of natural language  ...  With the development of biomedical language understanding benchmarks, Artificial Intelligence applications are widely used in the medical field.  ...  A significant trend is the emergence of multi-task leaderboards, such as GLUE (General Language Understanding Evaluation) and CLUE (Chinese Language Understanding Evaluation).  ... 
doi:10.18653/v1/2022.acl-long.544 fatcat:6yhygynowbeipelilmxdajwnoy

ClueGraphSum: Let Key Clues Guide the Cross-Lingual Abstractive Summarization [article]

Shuyu Jiang, Dengbiao Tu, Xingshu Chen, Rui Tang, Wenxian Wang, Haizhou Wang
2022 arXiv   pre-print
Cross-Lingual Summarization (CLS) is the task to generate a summary in one language for an article in a different language.  ...  Therefore, we first propose a clue-guided cross-lingual abstractive summarization method to improve the quality of cross-lingual summaries, and then construct a novel hand-written CLS dataset for evaluation  ...  Cross-lingual summarization is the task to compress an article in a source language (e.g. English) into a summary in a different target language (e.g. Chinese).  ... 
arXiv:2203.02797v2 fatcat:oczg6o7hfvfrxmutic3zwm6xnq

A Computational Approach to Find Deceptive Opinions by Using Psycholinguistic Clues

Mayank Saini, Aditi Sharan
2017 International Journal of Engineering and Technology  
The product reviews and the blogs play a vital role in giving the insight to end user for making a decision.  ...  This work primarily focuses on enhancing the accuracy of existing deceptive opinion spam classifiers using psycholinguistic/sociolinguistic deceptive clues.  ...  One of the possible future direction to evaluate these deception clues to other domains.  ... 
doi:10.21817/ijet/2017/v9i3/1709030248 fatcat:w5tw6e7agbfspciiavg7zwerau

LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization [article]

Weidong Guo, Mingjun Zhao, Lusheng Zhang, Di Niu, Jinwen Luo, Zhenhua Liu, Zhenyang Li, Jianbo Tang
2021 arXiv   pre-print
range of Natural Language Understanding (NLU) tasks.  ...  Extensive experiments conducted on CLUE and SuperGLUE demonstrate that our method achieves comprehensive improvements on a wide variety of NLU tasks in both Chinese and English with little extra inference  ...  In our experiments, all the Chinese PLMs are evaluated on Chinese Language Understanding Evaluation (CLUE) (Liang Xu, 2020) which is a comprehensive language understanding benchmark developed for Chinese  ... 
arXiv:2108.00801v1 fatcat:lk2lzmu4vrfadiunhizvyvdll4

FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark [article]

Liang Xu, Xiaojing Lu, Chenyang Yuan, Xuanwei Zhang, Huilin Xu, Hu Yuan, Guoao Wei, Xiang Pan, Xin Tian, Libo Qin, Hu Hai
2021 arXiv   pre-print
In this paper, we introduce the Chinese Few-shot Learning Evaluation Benchmark (FewCLUE), the first comprehensive few-shot evaluation benchmark in Chinese.  ...  Pretrained Language Models (PLMs) have achieved tremendous success in natural language understanding tasks.  ...  Our contributions are: • We construct the first systematic and comprehensive Few-shot Chinese Language Understanding Evaluation benchmark, and provide strong baselines and human evaluation.  ... 
arXiv:2107.07498v2 fatcat:ljx2nma3b5aa3ix2pzyadnkgnu

Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese [article]

Zhuosheng Zhang, Hanqing Zhang, Keming Chen, Yuhang Guo, Jingyun Hua, Yulong Wang, Ming Zhou
2021 arXiv   pre-print
Our lightweight model has achieved new state-of-the-art results on the widely-used CLUE benchmark with our optimized pre-training and fine-tuning techniques.  ...  range of language and vision tasks.  ...  Experiments Tasks For downstream tasks for model evaluation, we use the Chinese Language Understanding Evaluation (CLUE) benchmark (Xu et al., 2020b) Setup We build the downstream models for the  ... 
arXiv:2110.06696v2 fatcat:uwbje6ftcbbzhltkvnhsox6osu

Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words [article]

Zhangyin Feng, Duyu Tang, Cong Zhou, Junwei Liao, Shuangzhi Wu, Xiaocheng Feng, Bing Qin, Yunbo Cao, Shuming Shi
2022 arXiv   pre-print
Furthermore, since the pipeline is language-independent, we train WordBERT for Chinese language and obtain significant gains on five natural language understanding datasets.  ...  Lastly, the analyse on inference speed illustrates WordBERT has comparable time cost to BERT in natural language understanding tasks.  ...  Clue: A chinese language understanding evaluation benchmark. arXiv preprint arXiv:2004.05986.  ... 
arXiv:2202.12142v1 fatcat:ui7agnwb4rbqfbjwu7qkxirpze

AMBERT: A Pre-trained Language Model with Multi-Grained Tokenization [article]

Xinsong Zhang, Pengshuai Li, Hang Li
2021 arXiv   pre-print
Experiments have been conducted on benchmark datasets for Chinese and English, including CLUE, GLUE, SQuAD and RACE.  ...  Pre-trained language models such as BERT have exhibited remarkable performances in many tasks in natural language understanding (NLU).  ...  Acknowledgments We thank the teams at ByteDance for providing the Chinese corpus and the Chinese word segmentation tool.  ... 
arXiv:2008.11869v4 fatcat:p2gay75havaqbepp3lfkcdx6wa

JGLUE: Japanese General Language Understanding Evaluation

Kentaro Kurihara, Daisuke Kawahara, Tomohide Shibata
2022 Journal of Natural Language Processing  
"CLUE: A Chinese Language Understanding Evaluation Benchmark." In COLING2020, pp. 4762-4772, Barcelona, Spain (Online).  ...  Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., and Bowman, S. (2018). "GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding."  ... 
doi:10.5715/jnlp.29.711 fatcat:tlaudwiqlrhqpoigtmvzcmi7hq

CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation [article]

Yunfan Shao, Zhichao Geng, Yitao Liu, Junqi Dai, Fei Yang, Li Zhe, Hujun Bao, Xipeng Qiu
2021 arXiv   pre-print
Different from previous Chinese PTMs, CPT is designed for both natural language understanding (NLU) and natural language generation (NLG) tasks.  ...  CPT consists of three parts: a shared encoder, an understanding decoder, and a generation decoder.  ...  Classification We evaluate the model on the Chinese Language Understanding Evaluation Benchmark (CLUE) (Xu et al. 2020) , which contains text classification TNEWS, IFLYTEK, natural language inference  ... 
arXiv:2109.05729v3 fatcat:a65tgy3zvzehbprz6i3v2zq7bu

OCNLI: Original Chinese Natural Language Inference [article]

Hai Hu, Kyle Richardson, Liang Xu, Lu Li, Sandra Kuebler, Lawrence S. Moss
2020 arXiv   pre-print
limited to English due to a lack of reliable datasets for most of the world's languages.  ...  performance gap), making it a challenging new resource that we hope will help to accelerate progress in Chinese NLU.  ...  This work was supported by the CLUE benchmark and the Grant-in-Aid of Doctoral Research from Indiana University Graduate School.  ... 
arXiv:2010.05444v1 fatcat:oxsomovwjbhoxbofugsl4hbgea

A Comprehensive Exploration of Pre-training Language Models [article]

Tong Guo
2021 arXiv   pre-print
In this paper we explore the efficiency of various pre-trained language models. We pre-train a list of transformer-based models with the same amount of text and the same training steps.  ...  Recently, the development of pre-trained language models has brought natural language processing (NLP) tasks to the new state-of-the-art.  ...  BERT obtains state-of-the-art results on a wide array of Natural Language Processing (NLP) tasks, which include the GLUE [3] benchmark and CLUE [6] benchmark.  ... 
arXiv:2106.11483v3 fatcat:gwl5oh4efbhmpgimbwmvug7ii4
« Previous Showing results 1 — 15 out of 2,867 results