2019
ACL
ACL 2019
Better Character Language Modeling through Morphology
Abstract
AbstractWe incorporate morphological supervision into character language models (CLMs) via multitasking and show that this addition improves bits-per-character (BPC) performance across 24 languages, even when the morphology data and language modeling data are disjoint. Analyzing the CLMs shows that inflected words benefit more from explicitly modeling morphology than uninflected words, and that morphological supervision improves performance even as the amount of language modeling data grows. We then transfer morphological supervision across languages to improve performance in the low-resource setting.
🌉
Interdisciplinary Bridge
— Artificial Intelligence and Deep Learning and Interdisciplinary and Natural Language Processing
🧭
Keyword Pioneer
— morphological supervision
🐣
Hot Topic Early Bird
— multilingual language model
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio