← Search

Satoru Ozaki

2 accepted papers

2021

Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models

EMNLP 2021main

Commonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained during pre-training. Recent works only propose lightweight model updates as models ma…

2020

Automatic Interlinear Glossing for Under-Resourced Languages Leveraging Translations

COLING 2020main

Interlinear Glossed Text (IGT) is a widely used format for encoding linguistic information in language documentation projects and scholarly papers. Manual production of IGT takes time and requires linguistic expertise. We attempt to address this issue by creating automatic glossing models, using mod…