Fine-tune BERT for Extractive Summarization中文數據集LCSTS復現
目前有關於Fine-tune BERT for Extractive Summarization代碼只有英文數據集，未曾包含中文LCSTS的數據集，疫情在家期間嘗試將代碼轉換到中文數據集中。 ** 一、數據轉換篇 ** 根據源代碼中對數據格式的要求，一個story文件中包含原文和摘要，以@highlight進行區分。 所以我們首先需要將原LCSTS數據集進行轉換，原數據集的格式如下：經過轉換後的數
相關文章
- 1. Self-Supervised Learning for Contextualized Extractive Summarization
- 2. ACL2020 Heterogeneous Graph Neural Networks for Extractive Document Summarization
- 3. Heterogeneous Graph Neural Networks for Extractive Document Summarization
- 4. 【論文筆記】Heterogeneous Graph Neural Networks for Extractive Document Summarization
- 5. Extractive Summarization using Continuous Vector Space Models
- 6. 讀論文2018 ACL A unified model for extractive and abstractive summarization using inconsistency loss
- 7. 論文閱讀筆記《Ranking Sentences for Extractive Summarization with Reinforcement Learning》
- 8. SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documen
- 9. #Paper Reading# Neural Extractive Summarization with Side Information
- 10. bert 源碼解讀（基於gluonnlp finetune-classifier）
- 更多相關文章...
- • 現實生活中的 XML - XML 教程
- • R 繪圖 - 中文支持 - R 語言教程
- • Flink 數據傳輸及反壓詳解
- • Scala 中文亂碼解決
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Self-Supervised Learning for Contextualized Extractive Summarization
- 2. ACL2020 Heterogeneous Graph Neural Networks for Extractive Document Summarization
- 3. Heterogeneous Graph Neural Networks for Extractive Document Summarization
- 4. 【論文筆記】Heterogeneous Graph Neural Networks for Extractive Document Summarization
- 5. Extractive Summarization using Continuous Vector Space Models
- 6. 讀論文2018 ACL A unified model for extractive and abstractive summarization using inconsistency loss
- 7. 論文閱讀筆記《Ranking Sentences for Extractive Summarization with Reinforcement Learning》
- 8. SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documen
- 9. #Paper Reading# Neural Extractive Summarization with Side Information
- 10. bert 源碼解讀（基於gluonnlp finetune-classifier）