【論文閱讀筆記】Supervised Learning of Universal Sentence Representations from Natural Language Inference Da
本文是Facebook AI team發表在EMNLP2018，個人覺得比較有意思。文章主要目的是驗證NLP領域做遷移學習的可行性，在多種NLP任務上進行sentence level的embedding，實驗得出在NLI任務上進行預訓練的表達在遷移學習的效果上是最好的，作者認爲這是由於NLI任務使得句子向量中蘊含了句法或知識等對句子含義的理解。文章同時還探索了做NLI遷移學習的不同模
相關文章
- 1. [NLP論文閱讀] Supervised Learning of Universal Sentence Representations from NLI data
- 2. Machine Learning & Deep Learning 論文閱讀筆記
- 3. 文獻閱讀筆記-ALBERT ： A lite BERT for self-supervised learning of language representations
- 4. 論文筆記BERT: Bidirectional Encoder Representations from Transformers
- 5. 論文閱讀：Dual Supervised Learning for Natural Language Understanding and Generation
- 6. Natural Language Processing[論文合集]
- 7. 論文閱讀：DeepWalk Online Learning of Social Representations
- 8. 【論文閱讀】 A Decomposable Attention Model for Natural Language Inference
- 9. Stochastic Answer Networks for Natural Language Inference閱讀筆記
- 10. 《Enhanced LSTM for Natural Language Inference》論文總結
- 更多相關文章...
- • RSS 閱讀器 - RSS 教程
- • C# 文本文件的讀寫 - C#教程
- • Tomcat學習筆記（史上最全tomcat學習筆記）
- • JDK13 GA發佈：5大特性解讀
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. [NLP論文閱讀] Supervised Learning of Universal Sentence Representations from NLI data
- 2. Machine Learning & Deep Learning 論文閱讀筆記
- 3. 文獻閱讀筆記-ALBERT ： A lite BERT for self-supervised learning of language representations
- 4. 論文筆記BERT: Bidirectional Encoder Representations from Transformers
- 5. 論文閱讀：Dual Supervised Learning for Natural Language Understanding and Generation
- 6. Natural Language Processing[論文合集]
- 7. 論文閱讀：DeepWalk Online Learning of Social Representations
- 8. 【論文閱讀】 A Decomposable Attention Model for Natural Language Inference
- 9. Stochastic Answer Networks for Natural Language Inference閱讀筆記
- 10. 《Enhanced LSTM for Natural Language Inference》論文總結