自然语言处理国际前沿动态综述

国际前沿动态综述孙薇薇北京大学CCL每年都有都有国际前沿动态报告。所以，我重点介绍过去一年的最新热点Best paper或提名Presentation的时候人山人海两种论文简单问题复杂化复杂问题简单化各种各样的task不仅仅是序列标注Chris DyerEmily BenderJason EisnerMark JohnsonIs linguistic information useful for neural network architectures:can it improve state of the art neural architectures,and how should it be used?Does it help in building models that transfer better to new domains,new languages,new tasks,or for other limited annotated data scenarios?Are there any better implicit representations that neural networks can extract,whether similar or not to linguistic structures,that can be transferred or shared across tasks and,hence,serve as core language representation layers?结论是：ELMo很强大结论是：LISA在背起手的时候很不错句法分析显著提升了系统鲁棒性“标准”SRL：Arg0/AgentArg1/Patient降低了对标注者“专业性”的要求，使得普通人也可以充当标注者，有利于扩大数据量ACL2017的论文：找点儿新数据，定义个新任务，然后扔LSTM里2018仍然如此https:/Computational linguistics is the scientific study of language from a computational perspective.Work in computational linguistics is in some cases motivated from a scientific perspective in that one is trying to provide a computational explanation for a particular linguistic or psycholinguistic phenomenon;and in other cases the motivation may be more purely technological in that one wants to provide a working component of a speech or natural language system.数据很重要数据很重要数据很重要折腾数据很重要无标注数据（LM）异质数据（Multitask Learning）相关数据（MT平行语料）