Skip to content
conftrace_
2019 ACL ACL 2019

Cognate Projection for Low-Resource Inflection Generation

Abstract

AbstractWe propose cognate projection as a method of crosslingual transfer for inflection generation in the context of the SIGMORPHON 2019 Shared Task. The results on four language pairs show the method is effective when no low-resource training data is available.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Interdisciplinary and Natural Language Processing
🐣 Hot Topic Early Bird - low-resource language

Authors

Bradley Hauer, Amir Ahmad Habibi, Yixing Luan, Rashed Rubby Riyadh, Grzegorz Kondrak

Topics

Interdisciplinary > Linguistics > Computational Linguistics Machine Learning > Learning Types > Transfer Learning Natural Language Processing > Understanding > Morphology Natural Language Processing > Applications > Text Processing

Keywords

cross-lingual transfer low-resource language morphological processing inflection generation cognate projection
Download PDF

More from ACL 2019

All ACL 2019 papers →
Relevant and Informative Response Generation using Pointwise Mutual Information
Responsive and Self-Expressive Dialogue Generation
AX Semantics’ Submission to the SIGMORPHON 2019 Shared Task
Cross-Lingual Lemmatization and Morphology Tagging with Two-Stage Multilingual BERT Fine-Tuning
CBNU System for SIGMORPHON 2019 Shared Task 2: a Pipeline Model
Morpheus: A Neural Network for Jointly Learning Contextual Lemmatization and Morphological Tagging