Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss

ACL 2016  ·  Barbara Plank, Anders Søgaard, Yoav Goldberg ·

Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful for various NLP sequence modeling tasks, but little is known about their reliance to input representations, target languages, data set size, and label noise. We address these issues and evaluate bi-LSTMs with word, character, and unicode byte embeddings for POS tagging. We compare bi-LSTMs to traditional POS taggers across languages and data sizes. We also present a novel bi-LSTM model, which combines the POS tagging loss function with an auxiliary loss function that accounts for rare words. The model obtains state-of-the-art performance across 22 languages, and works especially well for morphologically complex languages. Our analysis suggests that bi-LSTMs are less sensitive to training data size and label corruptions (at small noise levels) than previously assumed.

PDF Abstract ACL 2016 PDF ACL 2016 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Part-Of-Speech Tagging Penn Treebank Bi-LSTM Accuracy 97.22 # 19
Part-Of-Speech Tagging UD Bi-LSTM Avg accuracy 96.40 # 4


No methods listed for this paper. Add relevant methods here