Methods for Amharic part-of-speech tagging

Gambäck, Björn; Olsson, Fredrik; Argaw, Atelach Alemu; Asker, Lars

doi:10.3115/1564508.1564527

Cited by 17 publications

(22 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alongside these hubs, a large number of individual researchers is working on African Language Technology, not only in Africa (Abdillahi et al 2007;Muhirwe 2007), but in the Western world as well (Hurskainen 1992;Gambäck et al 2009;Gasser 2010;Dione et al 2010;Shah et al 2010). It falls beyond the scope of this overview to introduce all of the individual researchers in the field, but we would like to refer to AfLaT.org for a fairly exhaustive bibliography on African Language Technology.…”

Section: A Brief Overview Of African Language Technologymentioning

confidence: 97%

Introduction to the special issue on African Language Technology

Pauw

Schryver

Pretorius

et al. 2011

Lang Resources & Evaluation

View full text Add to dashboard Cite

In today's digital multilingual world, language technology is crucial for providing access to information and opportunities for economic development. With approximately two thousand different languages, Africa is a multilingual continent par excellence, presenting acute challenges for those seeking to promote and use African languages in the areas of business development, education and relief aid. In recent times a number of researchers and institutions, both from Africa and elsewhere, have come forward to share the common goal of developing capabilities in language technology for African languages. In 2009 and 2010, the first two workshops on African Language Technology were organized (De Pauw et al. 2009, 2010a as a forum to bring together a wide range of researchers working in this domain.

show abstract

Section: A Brief Overview Of African Language Technologymentioning

confidence: 97%

Introduction to the special issue on African Language Technology

Pauw

Schryver

Pretorius

et al. 2011

Lang Resources & Evaluation

View full text Add to dashboard Cite

show abstract

“…This is mainly due: 1) to the absence of linguistical resources; 2) proprietary resources; 3) resources not in the electronic format. The most researched Ethiopic language is Amharic [1,2,9,11,13,23], which is also supported by Google. For the other languages as, e.g., Tigrinya, the research on different NLP topics are in their early stages (e.g., statistical machine translation from English to Tigrinya [3]).…”

Section: Related Workmentioning

confidence: 99%

Part-of-Speech Tagging via Deep Neural Networks for Northern-Ethiopic Languages

Kapočiūtė-Dzikienė

Tesfagergish

2020

ITC

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) have proven to be especially successful in the area of Natural Language Processing (NLP) and Part-Of-Speech (POS) tagging—which is the process of mapping words to their corresponding POS labels depending on the context. Despite recent development of language technologies, low-resourced languages (such as an East African Tigrinya language), have received too little attention. We investigate the effectiveness of Deep Learning (DL) solutions for the low-resourced Tigrinya language of the Northern-Ethiopic branch. We have selected Tigrinya as the testbed example and have tested state-of-the-art DL approaches seeking to build the most accurate POS tagger. We have evaluated DNN classifiers (Feed Forward Neural Network – FFNN, Long Short-Term Memory method – LSTM, Bidirectional LSTM, and Convolutional Neural Network – CNN) on a top of neural word2vec word embeddings with a small training corpus known as Nagaoka Tigrinya Corpus. To determine the best DNN classifier type, its architecture and hyper-parameter set both manual and automatic hyper-parameter tuning has been performed. BiLSTM method was proved to be the most suitable for our solving task: it achieved the highest accuracy equal to 92% that is 65% above the random baseline.

show abstract

“…A recent work investigated modeling POS tagging as an optimization problem using the genetic algorithm [1]. POS-tagging research for Amharic languages was mostly driven by a 210K-word news corpus that was tagged with 30 POS tags [6] Using this corpus, [8] reported various experiments applying Trigram'n'Tags (TnT), SVM, and maximum entropy algorithms. Furthermore, [10] identified inflectional and derivational patterns of Amharic words as features and improved tagging accuracy up to 90.95% using CRFs.…”

Section: Related Workmentioning

confidence: 99%

“…CRFs also solve the bias label problem that exists in maximum entropy Markov models (MEMMs) by training to predict the whole sequence correct instead of training to predict each label independently [12]. In the second approach, POS tagging is modeled as a classification problem and uses an SVM classifier [4] in a one-versus-therest multiclass scheme 8 . Both approaches are among the methods that have been successfully applied to develop stateof-the-art POS taggers 9 .…”

Section: Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Tigrinya Part-of-Speech Tagging with Morphological Patterns and the New Nagaoka Tigrinya Corpus

Tedla¹,

Yamamoto²,

Marasinghe³

2016

IJCA

View full text Add to dashboard Cite

This paper presents the first part-of-speech (POS) tagging research for Tigrinya (Semitic language) from the newly constructed Nagaoka Tigrinya Corpus. The raw text was extracted from a newspaper published in Eritrea in the Tigrinya language. This initial corpus was cleaned and formatted in plaintext and the Text Encoding Initiative (TEI) XML format. A tagset of 73 tags was designed, and the corpus for POS was manually annotated. This tagset encompasses three levels of grammatical information, which are the main POS categories, subcategories, and POS clitics. The POS tagged corpus contains 72,080 tokens. Tigrinya has a unique pattern of root-template morphology that can be utilized to infer POS categories. Subsequently, a supervised learning approach based on conditional random fields (CRFs) and support vector machines (SVMs) was applied, trained over contextual features of words and POS tags, morphological patterns, and affixes. A rigorous parameter optimization was performed and different combinations of features, data size, and tagsets were experimented upon to boost the overall accuracy, and particularly the prediction of POS for unknown words. For a reduced tagset of 20 tags, an overall accuracy of 90.89% was obtained on a stratified 10-fold cross validation. Enriching contextual features with morphological and affix features improved performance up to 41.01 percentage point, which is significant. General Termsnatural language processing, part-of-speech tagging

show abstract

Methods for Amharic part-of-speech tagging

Cited by 17 publications

References 16 publications

Introduction to the special issue on African Language Technology

Introduction to the special issue on African Language Technology

Part-of-Speech Tagging via Deep Neural Networks for Northern-Ethiopic Languages

Tigrinya Part-of-Speech Tagging with Morphological Patterns and the New Nagaoka Tigrinya Corpus

Contact Info

Product

Resources

About