- Uncovering divergent linguistic information in word embeddings with lessons for intrinsic and extrinsic evaluation . Mikel Artetxe, Gorka Labaka, Inigo Lopez-Gazpio, Eneko Agirre . CoNLL, 2018.
- The winner of CoNLL 2018 best paper award.
- It investigates different linguistic information encoded in word vectors by post-processing them through a linear transformation that adjusts the similarity orders.
- Useful resources:
- Deep contextualized word representations. Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer. NAACL, 2018.
- Context-based word representation developed by AllenNLP using a deep bidirectional language model.
- Useful resources: