Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology 2019
DOI: 10.18653/v1/w19-4202
|View full text |Cite
|
Sign up to set email alerts
|

Cognate Projection for Low-Resource Inflection Generation

Abstract: We propose cognate projection as a method of crosslingual transfer for inflection generation in the context of the SIGMORPHON 2019 Shared Task. The results on four language pairs show the method is effective when no low-resource training data is available.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2020
2020
2021
2021

Publication Types

Select...
5

Relationship

1
4

Authors

Journals

citations
Cited by 5 publications
(6 citation statements)
references
References 17 publications
0
6
0
Order By: Relevance
“…Notably, there exist NLP approaches such as the document classification approach of showing that indeed shared character-level information can facilitate cross-lingual transfer, but limit their analysis to same-script languages only. Specific to the the morphological inflection task, (Hauer et al, 2019) use cognate projection to augment low-resource data, while (Wiemerslage et al, 2018) explore the inflection task using inputs in phonological space as well as bundles of phonological features from PanPhon , showing improvements for both settings. Our work, in contrast, focuses on better cross-lingual transfer, attempting to combine the phonological and the orthographic space.…”
Section: Introductionmentioning
confidence: 99%
“…Notably, there exist NLP approaches such as the document classification approach of showing that indeed shared character-level information can facilitate cross-lingual transfer, but limit their analysis to same-script languages only. Specific to the the morphological inflection task, (Hauer et al, 2019) use cognate projection to augment low-resource data, while (Wiemerslage et al, 2018) explore the inflection task using inputs in phonological space as well as bundles of phonological features from PanPhon , showing improvements for both settings. Our work, in contrast, focuses on better cross-lingual transfer, attempting to combine the phonological and the orthographic space.…”
Section: Introductionmentioning
confidence: 99%
“…Five teams submitted systems for this subtask. Three teams (C ¸öltekin, 2019;Hauer et al, 2019;Madsack and Weißgraeber, 2019) did not find obvious improvements in their systems by adding in cross-lingual data. Anastasopoulos and Neubig (2019) submitted the overall winning system output with the highest average accuracy and third-ranked average Levenshtein distance.…”
Section: Cross-lingual Transfermentioning
confidence: 95%
“…Lexeme5 "draw" "sweep" "carry over the head" "wear" "ask" Model architecture engineering and data hallucination and augmentation techniques have seen consistent performance gains in current literature, but the effect of cross-lingual transfer for morphological inflection is less consistent. Some work has shown advances by conducting cross-lingual learning (Kann et al, 2017b;Anastasopoulos and Neubig, 2019;Murikinati and Anastasopoulos, 2020;Scherbakov, 2020;Peters and Martins, 2020), while some others have not found obvious improvements (Bergmanis et al, 2017;Rama and Çöltekin, 2018;Çöltekin, 2019;Hauer et al, 2019;Madsack and Weißgraeber, 2019). Wu et al (2020) shows the success of the Transformer architecture (Vaswani et al, 2017) for characterlevel transduction tasks, as is also supported by the results of the SIGMORPHON 2020 shared task 0 on morphological inflection (Vylomova et al, 2020).…”
Section: Introductionmentioning
confidence: 92%