Search Results for author: Sarana Nutanong

Found 13 papers, 10 papers with code

Space Decomposition for Sentence Embedding

1 code implementation5 Jun 2024 Wuttikorn Ponwitayarat, Peerat Limkonchotiwat, Ekapol Chuangsuwanich, Sarana Nutanong

The experimental results demonstrate that MixSP decreased the overlap representation between upper-range and lower-range classes significantly while outperforming competitors on STS and zero-shot benchmarks.

Semantic Textual Similarity Sentence +3

Learning Geometric-Aware Properties in 2D Representation Using Lightweight CAD Models, or Zero Real 3D Pairs

no code implementations CVPR 2023 Pattaramanee Arsomngern, Sarana Nutanong, Supasorn Suwajanakorn

We also achieve comparable results to SOTA methods trained on scene scans on four tasks in NYUv2, SUNRGB-D, indoor ADE20k, and indoor/outdoor COCO, despite using lightweight CAD models or pseudo data.

Scene Understanding

WangchanBERTa: Pretraining transformer-based Thai Language Models

2 code implementations24 Jan 2021 Lalita Lowphansirikul, Charin Polpanumas, Nawat Jantrakulchai, Sarana Nutanong

However, for a relatively low-resource language such as Thai, the choices of models are limited to training a BERT-based model based on a much smaller dataset or finetuning multi-lingual models, both of which yield suboptimal downstream performance.

Language Modelling Sentence +2

Cannot find the paper you are looking for? You can Submit a new open access paper.