no code implementations • NAACL (SMM4H) 2021 • Alham Fikri Aji, Made Nindyatama Nityasya, Haryo Akbarianto Wibowo, Radityo Eko Prasojo, Tirana Fatyanosa
This paper describes our team’s submission for the Social Media Mining for Health (SMM4H) 2021 shared task.
no code implementations • 19 Mar 2024 • Mirza Alim Mutasodirin, Radityo Eko Prasojo, Achmad F. Abka, Hanif Rasyidi
Using the best hack found, we then compare 512, 256, and 128 tokens length.
1 code implementation • 19 Mar 2024 • Mirza Alim Mutasodirin, Radityo Eko Prasojo
In this study, we investigate the performance of document truncation and summarization in text classification tasks.
1 code implementation • 2 Nov 2023 • Haryo Akbarianto Wibowo, Erland Hilman Fuadi, Made Nindyatama Nityasya, Radityo Eko Prasojo, Alham Fikri Aji
Unlike the previous Indonesian COPA dataset (XCOPA-ID), COPAL-ID incorporates Indonesian local and cultural nuances, and therefore, provides a more natural portrayal of day-to-day causal reasoning within the Indonesian cultural sphere.
no code implementations • 5 Jun 2023 • Made Nindyatama Nityasya, Haryo Akbarianto Wibowo, Alham Fikri Aji, Genta Indra Winata, Radityo Eko Prasojo, Phil Blunsom, Adhiguna Kuncoro
This evidence-based position paper critiques current research practices within the language model pre-training literature.
2 code implementations • 31 May 2022 • Genta Indra Winata, Alham Fikri Aji, Samuel Cahyawijaya, Rahmad Mahendra, Fajri Koto, Ade Romadhony, Kemal Kurniawan, David Moeljadi, Radityo Eko Prasojo, Pascale Fung, Timothy Baldwin, Jey Han Lau, Rico Sennrich, Sebastian Ruder
In this work, we focus on developing resources for languages in Indonesia.
no code implementations • PACLIC 2021 • Alham Fikri Aji, Tirana Noor Fatyanosa, Radityo Eko Prasojo, Philip Arthur, Suci Fitriany, Salma Qonitah, Nadhifa Zulfa, Tomi Santoso, Mahendra Data
We release our synthetic parallel paraphrase corpus across 17 languages: Arabic, Catalan, Czech, German, English, Spanish, Estonian, French, Hindi, Indonesian, Italian, Dutch, Romanian, Russian, Swedish, Vietnamese, and Chinese.
1 code implementation • 29 Mar 2022 • Rendi Chevi, Radityo Eko Prasojo, Alham Fikri Aji, Andros Tjandra, Sakriani Sakti
We present Nix-TTS, a lightweight TTS achieved via knowledge distillation to a high-quality yet large-sized, non-autoregressive, and end-to-end (vocoder-free) TTS teacher model.
no code implementations • ACL 2022 • Alham Fikri Aji, Genta Indra Winata, Fajri Koto, Samuel Cahyawijaya, Ade Romadhony, Rahmad Mahendra, Kemal Kurniawan, David Moeljadi, Radityo Eko Prasojo, Timothy Baldwin, Jey Han Lau, Sebastian Ruder
NLP research is impeded by a lack of resources and awareness of the challenges presented by underrepresented languages and dialects.
no code implementations • 3 Jan 2022 • Made Nindyatama Nityasya, Haryo Akbarianto Wibowo, Rendi Chevi, Radityo Eko Prasojo, Alham Fikri Aji
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.
no code implementations • 30 Dec 2020 • Asrul Sani Ariesandy, Mukhlis Amien, Alham Fikri Aji, Radityo Eko Prasojo
Neural machine translation (NMT) is typically domain-dependent and style-dependent, and it requires lots of training data.
no code implementations • 16 Dec 2020 • Made Nindyatama Nityasya, Haryo Akbarianto Wibowo, Radityo Eko Prasojo, Alham Fikri Aji
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 and utilization cost.
1 code implementation • 6 Nov 2020 • Haryo Akbarianto Wibowo, Tatag Aziz Prawiro, Muhammad Ihsan, Alham Fikri Aji, Radityo Eko Prasojo, Rahmad Mahendra, Suci Fitriany
In this work, we address a style-transfer from informal to formal Indonesian as a low-resource machine translation problem.
1 code implementation • LREC 2020 • Tri Wahyu Guntara, Alham Fikri Aji, Radityo Eko Prasojo
In the context of Machine Translation (MT) from-and-to English, Bahasa Indonesia has been considered a low-resource language, and therefore applying Neural Machine Translation (NMT) which typically requires large training dataset proves to be problematic.