no code implementations • WMT (EMNLP) 2021 • Lintang Sutawika, Jan Christian Blaise Cruz
In this paper, we describe the submission of the joint Samsung Research Philippines-Konvergen AI team for the WMT’21 Large Scale Multilingual Translation Task - Small Track 2.
no code implementations • 25 Oct 2023 • Jan Christian Blaise Cruz
In this paper, we describe the constrained MT systems submitted by Samsung R&D Institute Philippines to the WMT 2023 General Translation Task for two directions: en$\rightarrow$he and he$\rightarrow$en.
no code implementations • 23 May 2023 • Ruochen Zhang, Samuel Cahyawijaya, Jan Christian Blaise Cruz, Genta Indra Winata, Alham Fikri Aji
Multilingual Large Language Models (LLMs) have recently shown great capabilities in a wide range of tasks, exhibiting state-of-the-art performance through zero-shot or few-shot prompting methods.
no code implementations • 23 Mar 2023 • Zheng-Xin Yong, Ruochen Zhang, Jessica Zosa Forde, Skyler Wang, Arjun Subramonian, Holy Lovenia, Samuel Cahyawijaya, Genta Indra Winata, Lintang Sutawika, Jan Christian Blaise Cruz, Yin Lin Tan, Long Phan, Rowena Garcia, Thamar Solorio, Alham Fikri Aji
While code-mixing is a common linguistic practice in many parts of the world, collecting high-quality and low-cost code-mixed data remains a challenge for natural language processing (NLP) research.
no code implementations • 7 Apr 2022 • Dan John Velasco, Axel Alba, Trisha Gail Pelagio, Bryce Anthony Ramirez, Unisse Chua, Briane Paul Samson, Jan Christian Blaise Cruz, Charibeth Cheng
The resulting sense inventory and synonym sets can be used in automatically creating a wordnet.
no code implementations • 6 Apr 2022 • Gabriel Louis Tan, Adrian Paule Ty, Schuyler Ng, Denzel Adrian Co, Jan Christian Blaise Cruz, Charibeth Cheng
Lastly, we published the first Filipino conversational response generator capable of generating responses related to the previous 3 responses.
no code implementations • 20 Nov 2021 • Lintang Sutawika, Jan Christian Blaise Cruz
In this paper, we describe the submission of the joint Samsung Research Philippines-Konvergen AI team for the WMT'21 Large Scale Multilingual Translation Task - Small Track 2.
no code implementations • LREC 2022 • Jan Christian Blaise Cruz, Charibeth Cheng
In this paper, we improve on existing language resources for the low-resource Filipino language in two ways.
1 code implementation • 22 Oct 2020 • Jan Christian Blaise Cruz, Jose Kristian Resabal, James Lin, Dan John Velasco, Charibeth Cheng
Lastly, we perform analyses on transfer learning techniques to shed light on their true performance when operating in low-data domains through the use of degradation tests.
1 code implementation • 5 May 2020 • Jan Christian Blaise Cruz, Charibeth Cheng
We analyze our pretrained model's degradation speeds and look towards the use of this method for comparing models aimed at operating within the low-resource setting.
4 code implementations • 3 May 2020 • Luis Enrico Lopez, Diane Kathryn Cruz, Jan Christian Blaise Cruz, Charibeth Cheng
Question generation (QG) is a natural language generation task where a model is trained to ask questions corresponding to some input text.
1 code implementation • LREC 2020 • Jan Christian Blaise Cruz, Julianne Agatha Tan, Charibeth Cheng
Second, we benchmark Transfer Learning (TL) techniques and show that they can be used to train robust fake news classifiers from little data, achieving 91% accuracy on our fake news dataset, reducing the error by 14% compared to established few-shot baselines.
2 code implementations • 30 Jun 2019 • Jan Christian Blaise Cruz, Charibeth Cheng
Unlike mainstream languages (such as English and French), low-resource languages often suffer from a lack of expert-annotated corpora and benchmark resources that make it hard to apply state-of-the-art techniques directly.