Publication

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

Üstün, A., van der Goot, R., Bouma, G. & van Noord, G., 2-Aug-2019. 16 p.

Research output: Contribution to conferencePaperAcademic

Copy link to clipboard

Documents

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

    Final publisher's version, 305 KB, PDF-document

    Request copy

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
CountryItaly
CityFlorence
Period02/08/201902/08/2019

Event

16th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology

02/08/201902/08/2019

Florence, Italy

Event: Workshop

View graph of relations

ID: 86483918