Intrinsic Evaluation of Bangla Word Embeddings

Sadman, Nafiz; Sadmanee, Akib; Tanveer, Md. Iftekhar; Amin, M. Ashraful; Ali, Amin Ahsan

doi:10.1109/icbslp47725.2019.201506

Cited by 1 publication

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…aimed to solve 14 Indian languages NLP problems, but the generated models are not considered intrinsic evaluations. To best of our knowledge, only single research was conducted concerning Bengali word embedding using Word2Vec (Sadman et al, 2019). However, this work considered only intrinsic evaluations with a self-build dataset.…”

Section: Related Workmentioning

confidence: 99%

Towards Bengali Word Embedding: Corpus Creation, Intrinsic and Extrinsic Evaluations

Hossain¹,

Hoque²

2020

Preprint

View full text Add to dashboard Cite

Distributional word vector representation orword embedding has become an essential ingredient in many natural language processing (NLP) tasks such as machine translation, document classification, information retrieval andquestion answering. Investigation of embedding model helps to reduce the feature space and improves textual semantic as well as syntactic relations.This paper presents three embedding techniques (such as Word2Vec, GloVe, and FastText) with different hyperparameters implemented on a Bengali corpusconsists of180 million words. The performance of the embedding techniques is evaluated with extrinsic and intrinsic ways. Extrinsic performance evaluated by text classification, which achieved a maximum of 96.48% accuracy. Intrinsic performance evaluatedby word similarity (e.g., semantic, syntactic and relatedness) and analogy tasks. The maximum Pearson (&circ;r) correlation accuracy of 60.66% (Ss&circ;r) achieved for semantic similarities and 71.64% (Sy&circ;r) for syntactic similarities whereas the relatedness obtained 79.80% (Rs&circ;r). The semantic word analogy tasks achieved 44.00% of accuracy while syntactic word analogy tasks obtained 36.00%

show abstract

Section: Related Workmentioning

confidence: 99%