@inproceedings{kondratyuk-etal-2018-lemmatag,
    title = "{L}emma{T}ag: Jointly Tagging and Lemmatizing for Morphologically Rich Languages with {BRNN}s",
    author = "Kondratyuk, Daniel  and
      Gaven{\v{c}}iak, Tom{\'a}{\v{s}}  and
      Straka, Milan  and
      Haji{\v{c}}, Jan",
    editor = "Riloff, Ellen  and
      Chiang, David  and
      Hockenmaier, Julia  and
      Tsujii, Jun{'}ichi",
    booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
    month = oct # "-" # nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/D18-1532/",
    doi = "10.18653/v1/D18-1532",
    pages = "4921--4928",
    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."
}