Crowdsourcing and Validating Event-focused Emotion Corpora for German and English 一个德英双语的 parallel sentiment (emotion) analysis数据集. 情感分类模型可以直接应用于另一种语言上（通过翻译模型翻译），performance 不会下降。 Leap-LSTM: Enhanci ...

我认为是18年NLP领域最好滴工作，google真是如有天助，jacob刚去就搞了个大新闻。ELMo 18年naacl斩获best paper的时候其实我还不是特别感冒，但是BERT真是让pre-train上了一个大台阶。为什么真么说呢，首先，BERT的pre-train and fine-tune真是相比其他工作而言非常优雅了，特别是fine-tune阶段简直可以称之为傻瓜式；第二，效果惊人，在 ...

NAACL 2019 IntuitionThe standard setup for unsupervised structure learning is to define a generative model over observed data (e.g. sentence) and unobserved structure (e.g. parse tree, part-of-speech ...

This paper proposed a And-Or Graph network. Intuition and MotivationUnify and integrate building block. Build block is the basic component in popular network framework like Inception modules in Google ...

3.25-3.31 A Structured Self-attentive Sentence Embedding. matrix attention + penalty Learning Hierarchical Structures On-The-Fly with a Recurrent-Recursive Model for Sequences discretized structure, ...

目的目前现有的翻译软件 (google translator) 在日中翻译时使用英语进行“桥接”，这种先将日文翻译成英语再由英语翻译成中文的方法效果非常差，特别时翻译小说的时候。当然这是由于缺乏大量中日对应语料的无奈之举。 针对有对应语料的商用翻译软件 (百度，小牛)，由于使用的大量训练数据是类似于联合国正式文件，合同之类的语料，在翻译轻小说的时候对于一些简写，轻小说特有的缩写，以及涉及奇幻，情色 ...

这篇 paper 写的非常好，总结了近年来深度学习和有向图模型结合的部分工作。 由于有部分内容，特别是 Amortized Variational Inference 我还不是特别懂，所以暂时胡乱写写，以后有时间可能还会更新 （咕咕咕）。 我主要分为三个部分进行介绍： Models, Objective 和 Inference Method. ModelsDiscrete Models 考虑纯图模 ...

It is a interesting work that it learns text template during generation sentence from knowledge. Template is really useful since sentences are be written more based on templates than on words one by o ...

This work comes from Tommi Jaakkola. In vision, style transfer is a mature work. But in language, there not so many attention paid on this. Many work learning style transfer from parallel data, but ac ...

BriefThis work focus on commonsense knowledge. As described in this paper, they propose a new commonsense approach to address two problem: How to mine and represent different kinds of implicit knowl ...