Neural machine translation with a polysynthetic low resource language

Ortega, John E.; Mamani, Richard Castro; Cho, Kyunghyun

doi:10.1007/s10590-020-09255-9

Cited by 23 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One such avenue of future work would be to broaden our analysis to more languages and include languages that are higher-resourced but morphologically rich and as well as ones that are lower-resourced but morphologically poor. Ortega et al (2021), which we encountered during preparation of the final version of this paper, began to address these questions by comparing Morfessor with BPE and their own BPE variant on Finnish, Quechua and Spanish.…”

Section: Discussionmentioning

confidence: 99%

The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation

Sälevä¹,

Lignos²

2021

Preprint

View full text Add to dashboard Cite

This paper evaluates the performance of several modern subword segmentation methods in a low-resource neural machine translation setting. We compare segmentations produced by applying BPE at the token or sentence level with morphologically-based segmentations from LMVR and MORSEL. We evaluate translation tasks between English and each of Nepali, Sinhala, and Kazakh, and predict that using morphologically-based segmentation methods would lead to better performance in this setting. However, comparing to BPE, we find that no consistent and reliable differences emerge between the segmentation methods. While morphologically-based methods outperform BPE in a few cases, what performs best tends to vary across tasks, and the performance of segmentation methods is often statistically indistinguishable.

show abstract

Section: Discussionmentioning

confidence: 99%

The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation

Sälevä¹,

Lignos²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Particularly, the development of (MT) systems for indigenous languages in both South and North America, faces different challenges such as a high morphological richness, agglutination, polysynthesis, and orthographic variation (Mager et al, 2018b;Llitjós et al, 2005). In general, MT systems for these languages in the state-of-theart have been addressed by the sub-fields of machine translation: rule-based (Monson et al, 2006), statistical (Mager Hois et al, 2016) and neuralbased approaches (Ortega et al, 2020;Le and Sadat, 2020). Recently, NMT approaches (Stahlberg, 2020) have gained prominence; they commonly are based on sequence-to-sequence models using encoder-decoder architectures and attention mechanisms (Yang et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

“…Recently, NMT approaches (Stahlberg, 2020) have gained prominence; they commonly are based on sequence-to-sequence models using encoder-decoder architectures and attention mechanisms (Yang et al, 2020). From this perspective, different morphological segmentation techniques have been explored (Kann et al, 2018;Ortega et al, 2020) for Indigenous American languages.…”

Section: Related Workmentioning

confidence: 99%

Open Machine Translation for Low Resource South American Languages (AmericasNLP 2021 Shared Task Contribution)

Parida¹,

Panda²,

Dash³

et al. 2021

Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas

View full text Add to dashboard Cite

This paper describes the team ("Tamalli")'s submission to AmericasNLP2021 shared task on Open Machine Translation for low resource South American languages. Our goal was to evaluate different Machine Translation (MT) techniques, statistical and neural-based, under several configuration settings. We obtained the second-best results for the language pairs "Spanish-Bribri", "Spanish-Asháninka", and "Spanish-Rarámuri" in the category "Development set not used for training". Our performed experiments will serve as a point of reference for researchers working on MT with low-resource languages.

show abstract

“…To cope with the issue of complex morphology, Ortega et al (2020) build a translation model for Qeuchua, an Indigenous language of South America, with an integrated morphological segmentation method. To treat orthographic variation, Feldman and Coto-Solano (2020) standardize text with a rule-based system which converts diacritics and letters to contemporary orthographic convention.…”

Section: Mt Of Indigenous Languagesmentioning

confidence: 99%

IndT5: A Text-to-Text Transformer for 10 Indigenous Languages

Nagoudi¹,

Chen²,

Abdul-Mageed³

et al. 2021

Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas

View full text Add to dashboard Cite

Transformer language models have become fundamental components of natural language processing based pipelines. Although several Transformer models have been introduced to serve many languages, there is a shortage of models pre-trained for low-resource and Indigenous languages. In this work, we introduce IndT5, the first Transformer language model for Indigenous languages. To train IndT5, we build IndCorpus-a new dataset for ten Indigenous languages and Spanish. We also present the application of IndT5 to machine translation by investigating different approaches to translate between Spanish and the Indigenous languages as part of our contribution to the AmericasNLP 2021 Shared Task on Open Machine Translation. IndT5 and IndCorpus are publicly available for research. 1

show abstract

Neural machine translation with a polysynthetic low resource language

Cited by 23 publications

References 24 publications

The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation

The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation

Open Machine Translation for Low Resource South American Languages (AmericasNLP 2021 Shared Task Contribution)

IndT5: A Text-to-Text Transformer for 10 Indigenous Languages

Contact Info

Product

Resources

About