Towards JointUD: Part-of-speech Tagging and Lemmatization using Recurrent Neural Networks
This is an incremental improvement for natural language processing tasks, specifically in universal dependencies.
The paper tackled joint part-of-speech tagging and lemmatization using a recurrent neural network, extending an LSTM-based model to generate character-level sequences and jointly train on lemmas, tags, and features, but the results showed performance far from state-of-the-art.
This paper describes our submission to CoNLL 2018 UD Shared Task. We have extended an LSTM-based neural network designed for sequence tagging to additionally generate character-level sequences. The network was jointly trained to produce lemmas, part-of-speech tags and morphological features. Sentence segmentation, tokenization and dependency parsing were handled by UDPipe 1.2 baseline. The results demonstrate the viability of the proposed multitask architecture, although its performance still remains far from state-of-the-art.