| Resumen |
The task of automatically identifying a language used in a given text is called Language Identification (LI). India is a multilingual country and many Indians especially youths are comfortable with Hindi and English, in addition to their local languages. Hence, they often use more than one language to post their comments on social media. Texts containing more than one language are called “code-mixed texts” and are a good source of input for LI. Languages in these texts may be mixed at sentence level, word level or even at sub-word level. LI at word level is a sequence labeling problem where each and every word in a sentence is tagged with one of the languages in the predefined set of languages. For many NLP applications, using code-mixed texts, the first but very crucial preprocessing step will be identifying the languages in a given text. In order to address word level LI in code-mixed Kannada-English (Kn-En) texts, this work presents i) the construction of code-mixed Kn-En dataset called CoLI-Kenglish dataset, ii) code-mixed Kn-En embedding and iii) learning models using Machine Learning (ML), Deep Learning (DL) and Transfer Learning (TL) approaches. Code-mixed Kn-En texts are extracted from Kannada YouTube video comments to construct CoLI-Kenglish dataset and code-mixed Kn-En embedding. The words in CoLI-Kenglish dataset are grouped into six major categories, namely, “Kannada”, “English”, “Mixed-language”, “Name”, “Location” and “Other”. Code-mixed embeddings are used as features by the learning models and are created for each word, by merging the word vectors with sub-words vectors of all the sub-words in each word and character vectors of all the characters in each word. The learning models, namely, CoLI-vectors and CoLI-ngrams based on ML, CoLI-BiLSTM based on DL and CoLI-ULMFiT based on TL approaches are built and evaluated using CoLI-Kenglish dataset. The performances of the learning models illustrated, the superiority of CoLI-ngrams model, compared to other models with a macro average F1-score of 0.64. However, the results of all the learning models were quite competitive with each other. © 2022, Budapest Tech Polytechnical Institution. All rights reserved. |
