Cross-lingual, Character-Level Neural Morphological Tagging

Abstract

Even for common NLP tasks, sufficient supervision is not available in many languages -- morphological tagging is no exception. In the work presented here, we explore a transfer learning scheme, whereby we train character-level recurrent neural taggers to predict morphological taggings for high-resource languages and low-resource languages together. Learning joint character representations among multiple related languages successfully enables knowledge transfer from the high-resource languages to the low-resource ones, improving accuracy by up to 30% over a monolingual model.

Published as a conference paper at EMNLP 2017; Fixed minor typos and cleaned up formatting

References in corpus (4)

• Sequence to Sequence Learning with Neural Networks
• Natural Language Processing (almost) from Scratch
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Neural Morphological Tagging from Characters for Morphologically Rich Languages

Cited by in corpus (6)

• Cross-lingual Argumentation Mining: Machine Translation (and a bit of Projection) is All You Need!
• Multi Task Deep Morphological Analyzer: Context Aware Joint Morphological Tagging and Lemma Prediction
• Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification
• Zero-shot Neural Transfer for Cross-lingual Entity Linking
• Char-RNN for Word Stress Detection in East Slavic Languages
• Learning Noun Cases Using Sequential Neural Networks