Morphological Inflection Generation with Multi-space Variational
            Encoder-Decoders

Zhou, Chunting; Neubig, Graham

doi:10.18653/v1/k17-2005

Cited by 20 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We instead achieve state-of-the-art with a cheaper approach that simply intermixes a copying task which also encourages monotonicity. Data augmentation for inflection has been explored by Bergmanis et al (2017) and Zhou and Neubig (2017) among others. The work of Silfverberg et al (2017) is the most similar to ours, but as we already discussed, it has a few shortcomings that our approach addresses.…”

Section: Related Workmentioning

confidence: 99%

Pushing the Limits of Low-Resource Morphological Inflection

Anastasopoulos

Neubig

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

View full text Add to dashboard Cite

Recent years have seen exceptional strides in the task of automatic morphological inflection generation. However, for a long tail of languages the necessary resources are hard to come by, and state-of-the-art neural methods that work well under higher resource settings perform poorly in the face of a paucity of data. In response, we propose a battery of improvements that greatly improve performance under such low-resource conditions. First, we present a novel two-step attention architecture for the inflection decoder. In addition, we investigate the effects of cross-lingual transfer from single and multiple languages, as well as monolingual data hallucination. The macroaveraged accuracy of our models outperforms the state-of-the-art by 15 percentage points. 1 Also, we identify the crucial factors for success with cross-lingual transfer for morphological inflection: typological similarity and a common representation across languages.

show abstract

Section: Related Workmentioning

confidence: 99%

Pushing the Limits of Low-Resource Morphological Inflection

Anastasopoulos

Neubig

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the medium setting, the difference in accuracy is much more apparent. This is due to the fact that all of the top performing systems in the shared task also used either some type of data augmentation method (Zhou and Neubig (2017), Silfverberg et al (2017), Sudhakar and Kumar (2017), , Bergmanis et al (2017)) a hard alignment method (Makarov et al, 2017), or both (Nicolai et al, 2017). These results illustrate the common observation that neural systems require a large amount of data to be very accurate, which can be partially addressed by artificially expanding the training data, or enforcing some copy bias into the system.…”

Section: Experiments and Resultsmentioning

confidence: 87%

Phonological Features for Morphological Inflection

Wiemerslage¹,

Silfverberg²,

Hulden³

2018

Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology

View full text Add to dashboard Cite

Modeling morphological inflection is an important task in Natural Language Processing. In contrast to earlier work that has largely used orthographic representations, we experiment with this task in a phonetic character space, representing inputs as either IPA segments or bundles of phonological distinctive features. We show that both of these inputs, somewhat counterintuitively, achieve similar accuracies on morphological inflection, slightly lower than orthographic models. We conclude that providing detailed phonological representations is largely redundant when compared to IPA segments, and that articulatory distinctions relevant for word inflection are already latently present in the distributional properties of many graphemic writing systems.

show abstract

“…Silfverberg et al (2017) employ a data augmentation system splitting a word in three parts -inflectional prefix, word stem and inflectional suffixand then generating new words using existing preand suffixes. Further works using data augmentation are provided by Zhou and Neubig (2017) and Nicolai et al (2017).…”

Section: Enhancing Training Datamentioning

confidence: 99%

Finding the way from ä to a: Sub-character morphological inflection for the

Schröder¹,

Kamlot²,

Billing³

et al. 2018

Proceedings of The

View full text Add to dashboard Cite

In this paper we describe the system submitted by UHH to the CoNLL-SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection. We propose a neural architecture based on the concepts of UZH (Makarov et al., 2017), adding new ideas and techniques to their key concept and evaluating different combinations of parameters. The resulting system is a language-agnostic network model that aims to reduce the number of learned edit operations by introducing equivalence classes over graphical features of individual characters. We try to pinpoint advantages and drawbacks of this approach by comparing different network configurations and evaluating our results over a wide range of languages.

show abstract

Morphological Inflection Generation with Multi-space Variational Encoder-Decoders

Cited by 20 publications

References 8 publications

Pushing the Limits of Low-Resource Morphological Inflection

Pushing the Limits of Low-Resource Morphological Inflection

Phonological Features for Morphological Inflection

Finding the way from ä to a: Sub-character morphological inflection for the

Contact Info

Product

Resources

About