Neural Machine Translation for Amharic-English Translation

Gezmu, Andargachew Mekonnen; Nürnberger, Andreas; Bati, Tesfaye Bayu

doi:10.5220/0010383905260532

Cited by 5 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Knowless and Littell [18] proposed neural translation with translation memories for digitally low-resource American languages, such as German, Upper Sorbian, English, Inuktitut, Wixarika, Raramuri, Náhuatl, Guaraní, and Spanish, using ChrF and BLEU for evaluation. Additionally, Gezmu et al [19] discussed translation involving preprocessing, segmentation, and alignment in an Amharic-English parallel corpus, evaluated using neural networks with BLEU, BEER [20], and characTER metrics [21]. Dione et al [22] revealed approaches in neural translation with back-translation using French to Wolof and Wolof to English parallel corpora, employing BLEU for evaluation.…”

Section: Parallel Corporamentioning

confidence: 99%

“…Translation Techniques Tools Metrics [14] SMT Giza++, Moses WER 38, TER 0.86 [15] Transformer JoeyNMT BLEU 5 [16] Transformer Moses BLEU 5.67, ChrF 39.9 [17] Transformer, SMT Moses, OpenNMT BLEU 23.47 [18] Transformer Sockeye BLEU 38.2, ChrF 16.2 [19] Transformer, SMT Moses BLEU 33.0, BEER 0.576, characTER 0.705 [22] Transformer Not specified BLEU 37.5 [23] Transformer, SMT Fairseq, Moses BLEU 21.9, ChrF 0.484…”

Section: Referencesmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Translation between Mixtec to Spanish Languages Using Neural Networks

Santiago-Benito,

Córdova-Esparza,

Castro-Sánchez

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

This paper introduces a novel method for collecting and translating texts from the Mixtec to the Spanish language. The method comprises four primary steps. First, we collected a Mixtec–Spanish corpus that includes 4568 sentences from educational and religious domain texts. To enhance the parallel corpus, we generate synthetic data with GPT-3.5. Second, we cleaned the data with a semi-automatic approach followed by preprocessing and tokenization. In preprocessing, we removed stop words, duplicated sentences, special characters, and numbers and converted them to lowercase. Third, we performed semi-automatic alignment to find the correspondence of Mixtec–Spanish sentences to generate sentence-level aligned texts necessary for translation. Finally, we trained automatic translation models based on recurrent neural networks, bidirectional recurrent neural networks, and Transformers. Our system achieved a BLEU score of 95.66 for Mixtec-to-Spanish translation and 99.87 for Spanish-to-Mixtec translation. We also obtained a translation edit rate (TER) of 0.5 for Spanish-to-Mixtec and a TER of 16.5 for Mixtec-to-Spanish. Our research stands out as a pioneering effort in the field of automatic Mixtec-to-Spanish translation in Mexico, filling a gap identified in the current literature.

show abstract

Section: Parallel Corporamentioning

confidence: 99%

Section: Referencesmentioning

confidence: 99%

Automatic Translation between Mixtec to Spanish Languages Using Neural Networks

Santiago-Benito,

Córdova-Esparza,

Castro-Sánchez

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Gezmu et al [29] is the second attempt at Amharicto-English machine transliteration. In their work, they used machine transliteration as a tool (to facilitate vocabulary sharing) to improve the performance of Amharic-English MT.…”

Section: Amharic Transliterationmentioning

confidence: 99%

Baseline Transliteration Corpus for Improved English-Amharic Machine Translation

Biadgligne

Smaïli

2023

IJCAI

View full text Add to dashboard Cite

Machine translation (MT) between English and Amharic is one of the least studied and, performance-wise, least successful topics in the MT field. We therefore propose to apply corpus transliteration and augmentation techniques in this study to address this issue and improve MT performance for the language pairs. This paper presents the creation, the augmentation, and the use of an Amharic to English transliteration corpus for NMT experiments. The created corpus has a total of 450,608 parallel sentences before preprocessing and is used to train three different NMT architectures after preprocessing. These models are actually built using Recurrent Neural Networks with attention mechanism (RNN), Gated Recurrent Units (GRUs), and Transformers. Specifically, for Transformer-based experiments, three different Transformer models with different hyperparameters are created. Compared to previous works, the BLEU score results of all NMT models used in this study are improved. One of the three Transformer models, in particular, achieves the highest BLEU score ever recorded for the language pairs. Povzetek: Raziskava se ukvarja z izboljšanjem strojnega prevajanja (MT) med angleščino in amharščino, eno izmed najmanj proučevanih in uspešnih področij v MT. Predlagana je uporaba tehnike transliteracije in razširjanja korpusov. Izdelali so korpus za preizkušanje NMT, ki obsega 450,608 paralelnih stavkov.

show abstract

“…However, Amharic 1 is not included yet in the map of the QA datasets. Specific to Amharic there are attempts to develop datasets for other Natural Language Processing (NLP) tasks like sentiment analysis (Yimam et al, 2020), morphologically annotated corpus (Yeshambel et al, 2020), contemporary Amharic corpus (Gezmu et al, 2018), and parallel corpora for machine translation (Abate et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Amharic Question Answering for Biography, Definition, and Description Questions

Abedissa

Libsie

2019

Communications in Computer and Information Science

View full text Add to dashboard Cite

Question Answering (QA) returns concise answers or answer lists from natural language text given a context document. To advance robust models' development, large amounts of resources go into curating QA datasets. There is a surge of QA datasets for languages like English, however, this is not the case for Amharic. Amharic, the official language of Ethiopia, is the second most spoken Semitic language in the world. There is no published or publicly available Amharic QA dataset. Hence, to foster the research in Amharic QA, we present the first Amharic QA (AmQA) dataset. We crowdsourced 2628 question-answer pairs over 378 Wikipedia articles. Additionally, we run an XLMRLarge-based baseline model to spark opendomain QA research interest. The best-performing baseline achieves an F-score of 69.58 and 71.74 in reader-retriever QA and reading comprehension settings respectively.

show abstract

Neural Machine Translation for Amharic-English Translation

Cited by 5 publications

References 0 publications

Automatic Translation between Mixtec to Spanish Languages Using Neural Networks

Automatic Translation between Mixtec to Spanish Languages Using Neural Networks

Baseline Transliteration Corpus for Improved English-Amharic Machine Translation

Amharic Question Answering for Biography, Definition, and Description Questions

Contact Info

Product

Resources

About