TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Part-Of-Speech Tagging	Penn Treebank	Bi-LSTM	Accuracy	97.22	# 19
Part-Of-Speech Tagging	UD	Bi-LSTM	Avg accuracy	96.40	# 4

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multilingual-part-of-speech-tagging-with/part-of-speech-tagging-on-ud)](https://paperswithcode.com/sota/part-of-speech-tagging-on-ud?p=multilingual-part-of-speech-tagging-with)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multilingual-part-of-speech-tagging-with/part-of-speech-tagging-on-penn-treebank)](https://paperswithcode.com/sota/part-of-speech-tagging-on-penn-treebank?p=multilingual-part-of-speech-tagging-with)`

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.