0

Towards JointUD: Part-of-speech Tagging and Lemmatization using Recurrent Neural Networks

A multitask LSTM-based neural network enhanced for sequence tagging and character-level sequence generation shows promise, though it does not yet match state-of-the-art performance.

Year
2018
Venue
towards-jointud-part-of-speech-tagging-and-1
Authors
3
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/1809.03211ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

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.

Authors

3