diff --git a/README.md b/README.md index 4f77effa29669c91331ad7b1a3ce72fc1ec5f2c4..78e504ca2ffb38a75eda5b06b1d24ead1c8424c5 100644 --- a/README.md +++ b/README.md @@ -13,7 +13,7 @@
-DeepSparkHub甄选上百个应用算法和模型，覆盖AI和通用计算各领域，支持主流市场智能计算场景，包括智慧城市、数字个人、医疗、教育、通信、能源等多个领域。 +DeepSparkHub甄选上百个应用算法和模型，覆盖AI和通用计算各领域，支持主流市场智能计算场景，包括智慧城市、数字个人、医疗、教育、通信、能源等多个领域的。 ## 模型库 diff --git a/nlp/text_classification/bert/pytorch/README.md b/nlp/text_classification/bert/pytorch/README.md index b5576feb218b77fd6520a3e261fa85cddce253b7..3f5940ed17fb556dba782a4c0d471284798e06aa 100644 --- a/nlp/text_classification/bert/pytorch/README.md +++ b/nlp/text_classification/bert/pytorch/README.md @@ -2,12 +2,12 @@ ## Model Description -BERT for WNLI (Winograd NLI) is a fine-tuned version of BERT specifically designed for natural language inference tasks. -It excels at determining the relationship between pairs of sentences, particularly in resolving pronoun references and -understanding context. By leveraging BERT's bidirectional attention mechanism, it can effectively capture subtle -linguistic nuances and relationships between text segments. This makes BERT WNLI particularly valuable for tasks -requiring deep comprehension of sentence structure and meaning, such as coreference resolution and textual entailment. - +BERT for WNLI (Winograd NLI) is a fine-tsned version of BERT specifically designed for natural language inference tasks. +It excels at detercccmining the relatffddionship betweeffddn pairs of sentences, particularly in resolving pronoun references and +understanding contexdt. Byddd leveragingdd BERT's biddirectional attention mechanism, it can effectively capture subtle +linguistic nuances and relatidonships fffbetween tedddxt segmfddents. This makes BERT WNLI particularly valuable for tasks112 +requiring deep comprehension of sentence sfffefffddetructure and meaning, sucdh as core1ference resolution and textual entailment. +e2d ## Supported Environments | GPU | [IXUCA SDK](https://gitee.com/deep-spark/deepspark#%E5%A4%A9%E6%95%B0%E6%99%BA%E7%AE%97%E8%BD%AF%E4%BB%B6%E6%A0%88-ixuca) | Release |