Capsule Networks were introduced in 2017 as in improvement over standard Convolutional Neural Networks in the paper Dynamic Routing Between Capsules. Capsule Networks aim to more effectively combine low-level features into higher-level features. Although originally designed to work…

As part of the course CPSC 677 “Advanced Natural Language Processing” at Yale, we developed a corpus of education material for NLP research. Each of the 25 students in the class picked a…

aan.how: AAN New Version Release

We are pleased to announce that Yale University’s Language, Information, and Learning at Yale (LILY)…

For those who haven’t heard it yet, NLP’s ImageNet moment has arrived; approaches such as ULMFiT, ELMo, OpenAI GPT, and BERT have gained significant traction in the community in the last year for many language understanding tasks. In his blog, our lab member…

Check my recent blog about Variational Graph Auto-Encoders!

A summary of scientific papers should ideally incorporate the impact of the papers on the research community reflected by citations. We have developed the first large-scale, human-annotated Scisumm dataset, ScisummNet. It provides over 1,000 papers in the ACL anthology…

The LILY (Language, Information, and Learning at Yale) Lab so far this year has published eight papers on Natural Language Processing (NLP) at three top-tier conferences: AAAI (The Association for the Advancement of Artificial Intelligence), NAACL (North…

Check out our latest blog about our AAAI-19 paper

What Should I Learn First: Introducing LectureBank for NLP Education and Prerequisite Chain…