Terrence Szymanski

TL;DR: This paper surveys the current state of academic research related to diachronic word embeddings and semantic shifts detection, and proposes several axes along which these methods can be compared, and outlines the main challenges before this emerging subfield of NLP.

TL;DR: A survey of the current state of academic research related to diachronic word embeddings and semantic shifts detection can be found in this article, where the authors discuss the notion of semantic shifts, and then continue with an overview of the existing methods for tracing such time-related shifts with word embedding models.

TL;DR: It is shown that temporal word analogies can effectively be modeled with diachronic word embeddings, provided that the independent embedding spaces from each time period are appropriately transformed into a common vector space.

TL;DR: This work extracts n-gram features from the text at the letter, word, and syntactic level, and uses these to train a classifier on date-labeled training data, and incorporates date probabilities of syntactic features as estimated from a very large external corpus of books.

TL;DR: In this article, the authors present a software tool that employs state-of-the-art NLP and machine learning techniques to help newspaper editors compose effective headlines for online publication.