# Multi-Task Cross-Lingual Sequence Tagging from Scratch Source: [Multi-Task Cross-Lingual Sequence Tagging from Scratch]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:56:32.096Z Authors: Zhilin Yang, Ruslan Salakhutdinov, William Cohen Published: 2016-03-20T21:15:56.000Z ## Abstract We present a deep hierarchical recurrent neural network for sequence tagging. Given a sequence of words, our model employs deep gated recurrent units on both character and word levels to encode morphology and context information, and applies a conditional random field layer to predict the tags. Our model is task independent, language independent, and feature engineering free. We further extend our model to multi-task and cross-lingual joint training by sharing the architecture and parameters. Our model achieves state-of-the-art results in multiple languages on several benchmark tasks including POS tagging, chunking, and NER. We also demonstrate that multi-task and cross-lingual joint training can improve the performance in various cases. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Tag Prediction on Twitter dataset](): Tag prediction; Twitter dataset; Precision@1: 29.61. - [Chunking on CoNLL 2000 (test)](): Chunking; CoNLL 2000 (test); F1 Score: 94.66. - [Named Entity Recognition on CoNLL 2003 (test)](): Named Entity Recognition; CoNLL 2003 (test); F1 Score: 91.62. ## Original sources and implementation [Original paper]() [PDF]()