There is tremendous value buried text sources such as call center and chat dialogues, survey comments, product reviews, technical notes, legal contracts... How can we extract the signal we want amidst all the noise?
Amidst the growing popularity of modern machine learning and deep learning techniques, one of the biggest challenges is the ability to obtain large amounts of training data suitable for your use case. This post discusses how the analytical approach for Named Entity Recognition (NER) can help.
Word Mover's Distance (WMD) is a distance metric used to measure the dissimilarity between two documents, and its application in text analytics was introduced by a research group from Washington University in 2015. The group's paper, From Word Embeddings To Document Distances, was published on the 32nd International Conference on Machine
