Natural Language Processing (Almost) from Scratch
Natural Language Processing (Almost) from Scratch
复制标题
DOI：
10.5555/1953048.2078186
复制
发表时间：
2011-02
期刊：
影响因子：
--
通讯作者：
R. Collobert;J. Weston;L. Bottou;Michael Karlen;K. Kavukcuoglu;Pavel P. Kuksa
中科院分区：
文献类型：
--
作者：
R. Collobert;J. Weston;L. Bottou;Michael Karlen;K. Kavukcuoglu;Pavel P. Kuksa
我们提出了一种统一的神经网络体系结构和学习算法，可以应用于各种自然语言处理任务，包括言论部分标记，分解，命名实体识别和语义角色标签。这种多功能性是通过试图避免特定于任务的工程而实现的，因此可以忽略许多先验知识。我们的系统并没有利用针对每个任务的人造输入功能进行精心优化的人造功能，而是根据大量未标记的培训数据来学习内部表示。然后，这项工作被用作构建具有良好性能和最小计算要求的免费标记系统的基础。
We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is achieved by trying to avoid task-specific engineering and therefore disregarding a lot of prior knowledge. Instead of exploiting man-made input features carefully optimized for each task, our system learns internal representations on the basis of vast amounts of mostly unlabeled training data. This work is then used as a basis for building a freely available tagging system with good performance and minimal computational requirements.