SU-RUG at the CoNLL-SIGMORPHON 2017 shared task: Morphological Inflection with Attentional Sequence-to-Sequence Models
This work addresses morphological inflection for natural language processing, but it is incremental as it builds on existing sequence-to-sequence methods.
The paper tackled morphological inflection by developing an attentional sequence-to-sequence neural network model with LSTM cells, achieving a large margin over the baseline and ranking 4th in the high-resource track of the SIGMORPHON 2017 shared task.
This paper describes the Stockholm University/University of Groningen (SU-RUG) system for the SIGMORPHON 2017 shared task on morphological inflection. Our system is based on an attentional sequence-to-sequence neural network model using Long Short-Term Memory (LSTM) cells, with joint training of morphological inflection and the inverse transformation, i.e. lemmatization and morphological analysis. Our system outperforms the baseline with a large margin, and our submission ranks as the 4th best team for the track we participate in (task 1, high-resource).