Multi-Team: A Multi-attention, Multi-decoder Approach to Morphological Analysis

    OnderzoeksoutputAcademic

    Samenvatting

    This paper describes our submission to SIGMORPHON 2019 Task 2: Morphological analysis and lemmatization in context. Our model is a multi-task sequence to sequence neural network, which jointly learns morphological tagging and lemmatization. On the encoding side, we exploit character-level as
    well as contextual information. We introduce a multi-attention decoder to selectively focus on different parts of character and word sequences. To further improve the model, we train on multiple datasets simultaneously and
    use external embeddings for initialization. Our final model reaches an average morphological tagging F1 score of 94.54 and a lemma accuracy of 93.91 on the test data, ranking respectively 3rd and 6th out of 13 teams in the SIGMORPHON 2019 shared task.
    Originele taal-2English
    Aantal pagina's16
    StatusPublished - 2-aug-2019
    Evenement16th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology - Florence, Italy
    Duur: 2-aug-20192-aug-2019

    Workshop

    Workshop16th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
    Land/RegioItaly
    StadFlorence
    Periode02/08/201902/08/2019

    Citeer dit