问题驱动

知识图谱：

1. 不区分概念和实例 —> 上下位传递问题；[2018_EMNLP_Differentiating Concepts and Instances for Knowledge Graph Embedding]
2. 知识推理；引入强化学习；虚假样例；虚假路径 [2018_EMNLP_Multi-Hop Knowledge Graph Reasoning with Reward Shaping]

命名实体识别

1. 自动化标注代价大 [2018_EMNLP_Learning Named Entity Tagger using Domain-Specific Dictionary]

文档摘要

1. 单轮抽取 -> 迭代式多轮抽取；选择性读取 [2018_EMNLP_Iterative Document Representation Learning Towards Summarization with Polishing]

文本生成

1. seq2seq；同一输入同一输出 -> 同一输入不同输出且有区分性 [2018_EMNLP_Stylistic Chinese Poetry Generation via Unsupervised Style Disentanglement]

端到端

1. 引入auto-encoder [2018_EMNLP_Evaluating the Utility of Hand-crafted Features in Sequence Labelling]

问题驱动

原文：https://www.cnblogs.com/AIlover/p/9981319.html