知识图谱:
- 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]
- 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
- 自动化标注代价大 [2018_EMNLP_Learning Named Entity Tagger using Domain-Specific Dictionary]
文档摘要
- 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
- 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
- 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