[nlp] CopyNet

CopyNet
随着 ACL 2017 accepted paper list 的公布，可以看到一些经典的工作仍然在被各种应用和改进。其中不仅有引用量已经飙过 1000 的 attention mechanism，同时还有非常简单还用的 Pointer Network 和 CopyNet。

基于 Pointer Network 和 CopyNet 的一些重要和新鲜工作。：

[1] Jiatao Gu, Zhengdong Lu, Hang Li, et al. “Incorporating Copying Mechanism in Sequence-to-Sequence Learning”. ACL 2016.

[2] Caglar Gulcehre, Sungjin Ahn, Ramesh Nallapati et al. “Pointing the Unknown Words”. ACL 2016.

[3] Ziqiang Cao, Wenjie Li, Chuwei Luo and Sujian Li. “Joint Copying and Restricted Generation for Paraphrase”. AAAI 2017.

[4] Shizhu He, Kang Liu and Jun Zhao. “Generating Natural Answer by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning”. ACL 2017.

[5] Wang Ling, Dani Yogatama, Chris Dyer, Phil Blunsom. “Program Induction by Rationale Generation:Learning to Solve and Explain Algebraic Word Problems”. arXiv preprint 2017.

先来回顾一下同时发表在