no code implementations • EMNLP 2020 • Naoki Otani, Satoru Ozaki, Xingyuan Zhao, Yucen Li, Micaelah St Johns, Lori Levin
We propose a simple method for word translation of MWEs to and from English in ten languages: we first compile lists of MWEs in each language and then tokenize the MWEs as single tokens before training word embeddings.
1 code implementation • EMNLP 2021 • Kaixin Ma, Filip Ilievski, Jonathan Francis, Satoru Ozaki, Eric Nyberg, Alessandro Oltramari
In this paper, we investigate what models learn from commonsense reasoning datasets.
no code implementations • COLING 2020 • Xingyuan Zhao, Satoru Ozaki, Antonios Anastasopoulos, Graham Neubig, Lori Levin
Interlinear Glossed Text (IGT) is a widely used format for encoding linguistic information in language documentation projects and scholarly papers.