13 citations · 16 across the 5 of their papers we have counts for
6 papers
One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia
Alham Fikri Aji, Genta Indra Winata, Fajri Koto +9
NLP research is impeded by a lack of resources and awareness of the challenges presented by underrepresented languages and dialects. Focusing on the languages spoken in Indonesia,…
Which Student is Best? A Comprehensive Knowledge Distillation Exam for Task-Specific BERT Models
Made Nindyatama Nityasya, Haryo Akbarianto Wibowo, Rendi Chevi +2
We perform knowledge distillation (KD) benchmark from task-specific BERT-base teacher models to various student models: BiLSTM, CNN, BERT-Tiny, BERT-Mini, and BERT-Small. Our exper…
Synthetic Source Language Augmentation for Colloquial Neural Machine Translation
Asrul Sani Ariesandy, Mukhlis Amien, Alham Fikri Aji +1
Neural machine translation (NMT) is typically domain-dependent and style-dependent, and it requires lots of training data. State-of-the-art NMT models often fall short in handling…
Semi-Supervised Low-Resource Style Transfer of Indonesian Informal to Formal Language with Iterative Forward-Translation
Haryo Akbarianto Wibowo, Tatag Aziz Prawiro, Muhammad Ihsan +4
In its daily use, the Indonesian language is riddled with informality, that is, deviations from the standard in terms of vocabulary, spelling, and word order. On the other hand, cu…
Costs to Consider in Adopting NLP for Your Business
Made Nindyatama Nityasya, Haryo Akbarianto Wibowo, Radityo Eko Prasojo +1
Recent advances in Natural Language Processing (NLP) have largely pushed deep transformer-based models as the go-to state-of-the-art technique without much regard to the production…
Enabling Fine-grained RDF Data Completeness Assessment
Fariz Darari, Simon Razniewski, Radityo Eko Prasojo +1
Nowadays, more and more RDF data is becoming available on the Semantic Web. While the Semantic Web is generally incomplete by nature, on certain topics, it already contains complet…