Highlights of EMNLP 2017: Exciting Datasets, Return of the Clusters, and More!Brown clusters, an agglomerative, hierarchical clustering of word types based on contexts that was introduced in 1992 seem to come in vogue again. They were found to be particularly helpful for cross-lingual applications, while clusters were key features in several approaches: Mayhew et al. found that Brown cluster features were an important signal for cross-lingual NER. Botha et al. use word clus
