LemmaTag: Jointly Tagging and Lemmatizing for Morphologically-Rich Languages with BRNNs release_ujvw6dc7zbdw7p7kcypanmrja4

by Daniel Kondratyuk, Tomáš Gavenčiak, Milan Straka, Jan Hajič

Released as a article .

2018  

Abstract

We present LemmaTag, a featureless neural network architecture that jointly generates part-of-speech tags and lemmas for sentences by using bidirectional RNNs with character-level and word-level embeddings. We demonstrate that both tasks benefit from sharing the encoding part of the network, predicting tag subcategories, and using the tagger output as an input to the lemmatizer. We evaluate our model across several languages with complex morphology, which surpasses state-of-the-art accuracy in both part-of-speech tagging and lemmatization in Czech, German, and Arabic.
In text/plain format

Archived Files and Locations

application/pdf  562.8 kB
file_n72m5qm4pnbzhpfurki6img23a
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2018-08-27
Version   v2
Language   en ?
arXiv  1808.03703v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: f897c3ba-0f2a-467b-bbd3-537cd4581e9a
API URL: JSON