Toward a Lexicostatistic Classification of Ethiopian Languages

Bender, M. Lionel

doi:10.1515/9783111356167.377

Cited by 5 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…of these, 92 are living consisting of 87 indigineous and 5 non-indigenous while 1 extinct language [19]. Ethiopian languages belongs to the Afro-Asiatic language phy consisting of Semitic, Cushitic, Omotic of the Nilo-Saharan language family [36]. Among those languages, this study inspects Amharic from Semitic and Afaan Oromo from Cushitic language families.…”

Section: Ethiopian Languagesmentioning

confidence: 99%

Bilingual Hate Speech Detection on Social Media : Amharic and Afaan Oromo

Ababu,

Woldeyohannis,

Getaneh

2023

Preprint

View full text Add to dashboard Cite

Due to significant increases in internet penetration and the development of smartphone technology during the preceding couple of decades, many people have started using social media as a communication platform. Social media has grown to be one of the most significant components, with several benefits. However, technology also poses a number of threats, challenges, and barriers, such as hate speech, disinformation, and fake news. Hate speech detection is one of the many ways social media platforms can be accused of not doing enough to thwart hate speech on their platform. People in Bilingual and multinational societies commonly employ a code mix in both spoken and written communication. Among these, Amharic and Afaan Oromo language speakers frequently mix the two languages when conversing and posting on social media. The majority of previous study concentrated on identifying either technological favoured language or monolingual hate speech in Ethiopian languages; however, the availability of Bilingual communication in social media hampers the propagation of hate speech via social media. In this work, a Bilingual hate speech detection for Amharic and Afaan Oromo languages were conducted using four different deep learning classifiers (CNN, BiLSTM, CNN-BiLSTM, and BiGRU) and three feature extraction (Keras word embedding, word2vec, and FastText) techniques. According to the experiment, BiLSTM with FastText feature extraction is an outperforming the other algorithm by achieving a 78.05\% percent of accuracy for Bilingual Amharic Afaan Oromo hate speech detection. The FastText feature extraction overcomes the problem of out of vocabulary (OOV). Furthermore, we are working towards including others linguistic features of the languages to detect hate speech and make the resource available to facilitate further research in the area of Bilingual hate speech detection for other under-resourced Ethiopian languages.

show abstract

Section: Ethiopian Languagesmentioning

confidence: 99%

Bilingual Hate Speech Detection on Social Media : Amharic and Afaan Oromo

Ababu,

Woldeyohannis,

Getaneh

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…There are several ways to estimate LS between two certain languages. Historically, various lists have been proposed by experts like (Swadesh, 1955), (Bender, 1975) and (Haspelmath, 2008). Similar words (cognates) may appear among different languages mainly due to:…”

Section: Figure 1: Relative Positions Of Kurdish and English Languagesmentioning

confidence: 99%

Degree of Lexical Similarity between English and Kurdish

2022

IJSSHR

View full text Add to dashboard Cite

Indo-European languages are the native languages of the habitants of south and west Eurasia. It is the largest spoken language family in the world with 3.5 billion speakers, corresponding to 46% of the world population. Kurdish and English are genetically related, belong to the same family branch of languages, and are believed to have evolved from a common proto-language. Lexical Similarity measures the similarity and/or difference between a set of words from any given two languages. Despite the abundance of lexical similarity coefficients between various world languages in the literature, there are no available data on Kurdish, even though many Kurdish natives learn English as L2. The objective of this paper is to estimate the lexical similarity between two remotely related Indo-European languages. Our results showed (8.75%) and (9.75%) lexical similarity between English and Kurdish according to the Leipzig-Jakarta and Swadesh lists respectively; giving the average of (9.25%). In conclusion, English and Kurdish languages are related Indo-European languages and the lists used in this research are proven to be reliable in the comparison between the studied languages. These cognates can be helpful for the learners and teachers of Kurdish and Kurdish in their language acquisition process.

show abstract

“…There are several ways to estimate LS between two certain languages. Historically, various lists have been proposed by experts like (Swadesh 1955), (Bender 1975) and (Haspelmath 2008). Lexical cognates are used to create the lists used to calculate lexical similarity.…”

Section: Introductionmentioning

confidence: 99%

Kurdish and Persian: Dialects or Separate Languages?

Mahmood¹,

Rash²,

Rash,³

et al. 2023

IJSSHR

View full text Add to dashboard Cite

Although it is not quietly supported nowadays, some linguistics and orientalists believed/proposed that due to the large resemblance between the two and somehow mutual ineligibility, Kurdish is a dialect of Persian. The objective of this paper was to answer this hypothesis from a lexical point of view. Lexical Similarity measures the similarity and/or difference between a set of words from any given two languages. Despite the abundance of lexical similarity coefficients between various world languages in the literature, there are no available data on Kurdish and Persian, even though many Kurdish natives learn Persian as a second language. Our results showed (51.5 %) lexical similarity between Persian and Kurdish by using the Leipzig-Jakarta list. This result shows close proximity and common genetic roots between these two languages. However, it is not high enough to claim a dialect relation between the two; like, for example, 85% similarity index between Catalan and Spanish. Hence, this outcome, in a lexical point of view, is against the hypothesis of ‘Kurdish is a dialect of Persian’.

show abstract

Toward a Lexicostatistic Classification of Ethiopian Languages

Cited by 5 publications

References 0 publications

Bilingual Hate Speech Detection on Social Media : Amharic and Afaan Oromo

Bilingual Hate Speech Detection on Social Media : Amharic and Afaan Oromo

Degree of Lexical Similarity between English and Kurdish

Kurdish and Persian: Dialects or Separate Languages?

Contact Info

Product

Resources

About