Header

UZH-Logo

Maintenance Infos

Align and Copy: UZH at SIGMORPHON 2017 Shared Task for Morphological Reinflection


Makarov, Peter; Ruzsics, Tatiana; Clematide, Simon (2017). Align and Copy: UZH at SIGMORPHON 2017 Shared Task for Morphological Reinflection. In: 15th Annual SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology at CoNLL 2017, Vancouver, Canada, 3 August 2017 - 4 August 2017, 49-57.

Abstract

This paper presents the submissions by the University of Zurich to the SIGMORPHON 2017 shared task on morphological reinflection. The task is to predict the inflected form given a lemma and a set of morpho-syntactic features. We focus on neural network approaches that can tackle the task in a limited-resource setting. As the transduction of the lemma into the inflected form is dominated by copying over lemma characters, we propose two recurrent neural network architectures with hard monotonic attention that are strong at copying and, yet, substantially different in how they achieve this. The first approach is an encoder-decoder model with a copy mechanism. The second approach is a neural state-transition system over a set of explicit edit actions, including a designated COPY action. We experiment with character alignment and find that naive, greedy alignment consistently produces strong results for some languages. Our best system combination is the overall winner of the SIGMORPHON 2017 Shared Task 1 without external resources. At a setting with 100 training samples, both our approaches, as ensembles of models, outperform the next best competitor.

Abstract

This paper presents the submissions by the University of Zurich to the SIGMORPHON 2017 shared task on morphological reinflection. The task is to predict the inflected form given a lemma and a set of morpho-syntactic features. We focus on neural network approaches that can tackle the task in a limited-resource setting. As the transduction of the lemma into the inflected form is dominated by copying over lemma characters, we propose two recurrent neural network architectures with hard monotonic attention that are strong at copying and, yet, substantially different in how they achieve this. The first approach is an encoder-decoder model with a copy mechanism. The second approach is a neural state-transition system over a set of explicit edit actions, including a designated COPY action. We experiment with character alignment and find that naive, greedy alignment consistently produces strong results for some languages. Our best system combination is the overall winner of the SIGMORPHON 2017 Shared Task 1 without external resources. At a setting with 100 training samples, both our approaches, as ensembles of models, outperform the next best competitor.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

0 downloads since deposited on 14 Feb 2018
0 downloads since 12 months

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:4 August 2017
Deposited On:14 Feb 2018 17:02
Last Modified:18 Apr 2018 11:49
Publisher:Association for Computational Linguistics
Funders:European Research Council Grant No. 338875
OA Status:Hybrid
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.18653/v1/K17-2004
Official URL:http://www.aclweb.org/anthology/K17-2004

Download

Download PDF  'Align and Copy: UZH at SIGMORPHON 2017 Shared Task for Morphological Reinflection'.
Preview
Content: Published Version
Filetype: PDF
Size: 1MB
View at publisher