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

    Research output: Contribution to conferencePaperAcademic

    Abstract

    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.
    Original languageEnglish
    Number of pages16
    Publication statusPublished - 2-Aug-2019
    Event16th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology - Florence, Italy
    Duration: 2-Aug-20192-Aug-2019

    Workshop

    Workshop16th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
    Country/TerritoryItaly
    CityFlorence
    Period02/08/201902/08/2019

    Cite this