图 书 馆
自然语言处理的统一架构：多任务学习的深度神经网络A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning |
|
| 课程网址: | http://videolectures.net/icml08_collobert_uanl/ |
| 主讲教师: | Ronan Collobert |
| 开课单位: | 美国NEC实验室 |
| 开课时间: | 2008-07-30 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We describe a single convolutional neural network architecture that given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity tags, semantic roles, semantically similar words and the likelihood that the sentence makes sense (grammatically and semantically) using a language model. The entire network is trained jointly on all these tasks using weight-sharing, an instance of multitask learning. All the tasks use labeled data except the language model which is learnt from unlabeled text and represents a novel way of performing semi-supervised learning for the shared tasks. We show how both multitask learning and semi-supervised learning improve the generalization of the shared tasks, resulting in a learnt model with state-of-the-art performance. |
| 关 键 词: | 卷积神经网络结构; 语言模型; 多任务学习和半监督学习 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2021-05-14：yumf |
| 阅读次数: | 118 |