1 code implementation • EMNLP 2020 • Peerat Limkonchotiwat, Wannaphong Phatthiyaphaibun, Raheem Sarwar, Ekapol Chuangsuwanich, Sarana Nutanong
Like many Natural Language Processing tasks, Thai word segmentation is domain-dependent.
Ranked #1 on Thai Word Segmentation on WS160 (using extra training data)
no code implementations • Findings (EMNLP) 2021 • Nattapol Trijakwanich, Peerat Limkonchotiwat, Raheem Sarwar, Wannaphong Phatthiyaphaibun, Ekapol Chuangsuwanich, Sarana Nutanong
Cross-lingual Sentence Retrieval (CLSR) aims at retrieving parallel sentence pairs that are translations of each other from a multilingual set of comparable documents.
1 code implementation • Findings (NAACL) 2022 • Peerat Limkonchotiwat, Wuttikorn Ponwitayarat, Can Udomcharoenchaikit, Ekapol Chuangsuwanich, Sarana Nutanong
A common approach to CL-ReQA is to create a multilingual sentence embedding space such that question-answer pairs across different languages are close to each other.
1 code implementation • 24 Mar 2024 • Wannaphong Phatthiyaphaibun, Surapon Nonesung, Patomporn Payoungkhamdee, Peerat Limkonchotiwat, Can Udomcharoenchaikit, Jitkapat Sawatphol, Chompakorn Chaksangchaichot, Ekapol Chuangsuwanich, Sarana Nutanong
Our model is based on SEA-LION and a collection of instruction following datasets.
1 code implementation • 6 Nov 2023 • Peerat Limkonchotiwat, Wuttikorn Ponwitayarat, Lalita Lowphansirikul, Can Udomcharoenchaikit, Ekapol Chuangsuwanich, Sarana Nutanong
In this paper, we propose a framework called Self-supervised Cross-View Training (SCT) to narrow the performance gap between large and small PLMs.
1 code implementation • 17 Jun 2023 • Panuthep Tasawong, Wuttikorn Ponwitayarat, Peerat Limkonchotiwat, Can Udomcharoenchaikit, Ekapol Chuangsuwanich, Sarana Nutanong
One of the main challenges of dense retrieval in real-world settings is the handling of queries containing misspelled words.
1 code implementation • ICCV 2023 • Pitchaporn Rewatbowornwong, Nattanat Chatthee, Ekapol Chuangsuwanich, Supasorn Suwajanakorn
CLIP has enabled new and exciting joint vision-language applications, one of which is open-vocabulary segmentation, which can locate any segment given an arbitrary text query.
1 code implementation • 9 Aug 2022 • Wannaphong Phatthiyaphaibun, Chompakorn Chaksangchaichot, Peerat Limkonchotiwat, Ekapol Chuangsuwanich, Sarana Nutanong
However, most of these ASR models are available in English; only a minority of the models are available in Thai.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 28 Feb 2022 • Chawan Piansaddhayanon, Sakun Santisukwongchote, Shanop Shuangshoti, Qingyi Tao, Sira Sriswasdi, Ekapol Chuangsuwanich
Existing approaches utilize a two-stage pipeline: the detection stage for identifying the locations of potential mitotic cells and the classification stage for refining prediction confidences.
1 code implementation • NeurIPS 2021 • Konpat Preechakul, Chawan Piansaddhayanon, Burin Naowarat, Tirasan Khandhawit, Sira Sriswasdi, Ekapol Chuangsuwanich
Set prediction tasks require the matching between predicted set and ground truth set in order to propagate the gradient signal.
1 code implementation • 22 Oct 2020 • Konpat Preechakul, Sira Sriswasdi, Boonserm Kijsirikul, Ekapol Chuangsuwanich
In medical imaging, Class-Activation Map (CAM) serves as the main explainability tool by pointing to the region of interest.
no code implementations • 16 May 2020 • Burin Naowarat, Thananchai Kongthaworn, Korrawe Karunratanakul, Sheng Hui Wu, Ekapol Chuangsuwanich
Code-Switching (CS) remains a challenge for Automatic Speech Recognition (ASR), especially character-based models.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 8 Apr 2020 • Nannapas Banluesombatkul, Pichayoot Ouppaphan, Pitshaporn Leelaarporn, Payongkit Lakhan, Busarakum Chaitusaney, Nattapong Jaimchariyatam, Ekapol Chuangsuwanich, Wei Chen, Huy Phan, Nat Dilokthanakul, Theerawit Wilaiprasitporn
This is the first work that investigated a non-conventional pre-training method, MAML, resulting in a possibility for human-machine collaboration in sleep stage classification and easing the burden of the clinicians in labelling the sleep stages through only several epochs rather than an entire recording.
2 code implementations • Molecular & Cellular Proteomics 2019 • Korrawe Karunratanakul, Hsin-Yao Tang, David W. Speicher, Ekapol Chuangsuwanich, Sira Sriswasdi
Typical analyses of mass spectrometry data only identify amino acid sequences that exist in reference databases.
no code implementations • 4 Aug 2019 • Chanatip Saetia, Ekapol Chuangsuwanich, Tawunrat Chalothorn, Peerapon Vateekul
In the Thai sentence segmentation experiments, our model reduced the relative error by 7. 4% and 10. 5% compared with the baseline models on the Orchid and UGWC datasets, respectively.
no code implementations • 31 Aug 2018 • Patcharin Cheng, Phairot Autthasan, Boriwat Pijarana, Ekapol Chuangsuwanich, Theerawit Wilaiprasitporn
The focus is mainly on three types of brain responses: non-imagery EEG (\textit{background EEG}), (\textit{pure imagery}) EEG, and EEG during the transitional period between background EEG and pure imagery (\textit{transitional imagery}).
no code implementations • 5 Jul 2018 • Theerawit Wilaiprasitporn, Apiwat Ditthapron, Karis Matchaparn, Tanaboon Tongbuasirilai, Nannapas Banluesombatkul, Ekapol Chuangsuwanich
\textcolor{red}{We proposed a cascade of deep learning using a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs)}.
2 code implementations • 29 May 2018 • Itthi Chatnuntawech, Kittipong Tantisantisom, Paisan Khanchaitit, Thitikorn Boonkoom, Berkin Bilgic, Ekapol Chuangsuwanich
In this work, we develop a non-destructive rice variety classification system that benefits from the synergy between hyperspectral imaging and deep convolutional neural network (CNN).
no code implementations • 30 Oct 2015 • Yu Zhang, Ekapol Chuangsuwanich, James Glass, Dong Yu
In this paper, we investigate the use of prediction-adaptation-correction recurrent neural networks (PAC-RNNs) for low-resource speech recognition.