This is a demo of our State-of-the-art neural coreference resolution system. The open source code for Neural coref, our coreference system based on neural nets and spaCy, is on Github, and we explain in our Medium publication how the model works and how to train it.
In short, coreference is the fact that two or more expressions in a text – like pronouns or nouns – link to the same person or thing. It is a classical Natural language processing task, that has seen a revival of interest in the past two years as several research groups applied cutting-edge deep-learning and reinforcement-learning techniques to it. It is also one of the key building blocks to building conversational Artificial intelligences. If you like this demo please tweet about it 👍.