Discriminative neural sentence modeling by tree-based convolution | |
Mou, Lili ; Peng, Hao ; Li, Ge ; Xu, Yan ; Zhang, Lu ; Jin, Zhi | |
2015 | |
英文摘要 | This paper proposes a tree-based convolutional neural network (TBCNN) for discriminative sentence modeling. Our model leverages either constituency trees or dependency trees of sentences. The tree-based convolution process extracts sentences structural features, which are then aggregated by max pooling. Such architecture allows short propagation paths between the output layer and underlying feature detectors, enabling effective structural feature learning and extraction. We evaluate our models on two tasks: sentiment analysis and question classification. In both experiments, TBCNN outperforms previous state-of-the-art results, including existing neural networks and dedicated feature/rule engineering. We also make efforts to visualize the tree-based convolution process, shedding light on how our models work. ? 2015 Association for Computational Linguistics.; EI; 2315-2325 |
语种 | 英语 |
出处 | Conference on Empirical Methods in Natural Language Processing, EMNLP 2015 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/436873] |
专题 | 软件与微电子学院 |
推荐引用方式 GB/T 7714 | Mou, Lili,Peng, Hao,Li, Ge,et al. Discriminative neural sentence modeling by tree-based convolution. 2015-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论