https://aclweb.org/anthology/D18-1374
Michał Łukasik (currently at Google AI, previously in NLP group at the Sheffield University) will give a presentation on "Content Explorer: Recommending Novel Entities for a Document Writer” based on his EMNLP-2018 paper (). The talk will be in Exactum B119 this Friday (Feb 8th) at 10:00.
Title: Content Explorer: Recommending Novel Entities for a Document Writer Abstract: Background research is an essential part of document writing. Search engines are great for retrieving information once we know what to look for. However, the bigger challenge is often identifying topics for further research. Automated tools could help significantly in this discovery process and increase the productivity of the writer. In this paper, we formulate the problem of recommending topics to a writer. We consider this as a supervised learning problem and run a user study to validate this approach. We propose an evaluation metric and perform an empirical comparison of state-of-the-art models for extreme multi-label classification on a large data set. We demonstrate how a simple modification of the crossentropy loss function leads to improved results of the deep learning models.