(ACL2019)Open-DomainTargeted Sentiment Analysis via Span-Based Extraction and Classification
open-domain targeted任務主要分兩部分，第一步是把句子中的target檢測出來，第二步是對target進行情感分類。 文章提出了一種基於新的數據標註方式的方法，解決了傳統tag標註的搜索空間大且同一target下的不同單詞可能被歸入不同情感標籤的缺點，以bert爲基礎模型進行了實驗。 論文提出的Span-Based標註方法如下： 下圖表示的是論文整個模型的工作過程，提取出targ
相關文章
- 1. Sentiment Analysis resources
- 2. course1-3_supervised-ml-sentiment-analysis
- 3. Lab1:Sentiment Analysis（dictionary method）
- 4. Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM
- 5. 《Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree》閱讀筆記
- 6. Sparse Principal Component Analysis via Rotation and Truncation
- 7. Joint Event Extraction via Recurrent Neural Networks
- 8. 《A Joint Model of Term Exaction and Polarity Classification for Aspect-based Sentiment Analysis》閱讀筆記
- 9. SemEval2019Task3_ERC | (3) Using Deep Sentiment Analysis Models and Transfer Learning for ERC
- 10. 論文閱讀：Leveraging multimodal information for event summarization and concept-level sentiment analysis
- 更多相關文章...
- • W3C RDF and OWL 活動 - W3C 教程
- • XSL-FO table-and-caption 對象 - XSL-FO 教程
- • RxJava操作符（七）Conditional and Boolean
- • Flink 數據傳輸及反壓詳解
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. Sentiment Analysis resources
- 2. course1-3_supervised-ml-sentiment-analysis
- 3. Lab1:Sentiment Analysis（dictionary method）
- 4. Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM
- 5. 《Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree》閱讀筆記
- 6. Sparse Principal Component Analysis via Rotation and Truncation
- 7. Joint Event Extraction via Recurrent Neural Networks
- 8. 《A Joint Model of Term Exaction and Polarity Classification for Aspect-based Sentiment Analysis》閱讀筆記
- 9. SemEval2019Task3_ERC | (3) Using Deep Sentiment Analysis Models and Transfer Learning for ERC
- 10. 論文閱讀：Leveraging multimodal information for event summarization and concept-level sentiment analysis