Phrase embeddings
several representations are proposed to extend word representation for phrases ([Yin and Schütze, 2014](/doc/?; Yu and Dredze, 2015; Passos et al., 2014). However, they don’t use structured knowledge to derive phrase representations (as said [here](/doc/? [Sabastian Ruder](/tag/sebastian_ruder) in 2017 says the [following]( > explicitly modelling phrases has so far not shown significant improvements on downstream tasks that would justify the additional complexity (but hum: what's about NER - in particular if using external knowledge such as lexicons?)
Related Tags:
2 Documents (Long List