SU-RUG at the CoNLL-SIGMORPHON 2017 shared task: Morphological\n Inflection with Attentional Sequence-to-Sequence Models

2017/06/12 by Robert Östling, Johannes Bjerva, Östling, Robert +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1706.03499

openalex publication_date 2017/06/12 · openalex created_date 2022/10/01 · openalex updated_date 2026/07/28

Abstract

This paper describes the Stockholm University/University of Groningen\n(SU-RUG) system for the SIGMORPHON 2017 shared task on morphological\ninflection. Our system is based on an attentional sequence-to-sequence neural\nnetwork model using Long Short-Term Memory (LSTM) cells, with joint training of\nmorphological inflection and the inverse transformation, i.e. lemmatization and\nmorphological analysis. Our system outperforms the baseline with a large\nmargin, and our submission ranks as the 4th best team for the track we\nparticipate in (task 1, high-resource).\n

Citations

• Long Short-Term Memory
• Neural Machine Translation by Jointly Learning to Align and Translate

Related

• CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages
• The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection
• Finding the way from ä to a: Sub-character morphological inflection for the SIGMORPHON 2018 Shared Task
• SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological\n Inflection
• The SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion