Chinese New Word Discovery: From Traditional Unsupervised Methods to CNN‑Based Deep Learning

The article examines the challenge of out‑of‑vocabulary terms in Chinese e‑commerce NLP, reviews classic unsupervised metrics such as frequency, cohesion and neighbor entropy, and proposes a lightweight fully‑convolutional network inspired by image‑segmentation techniques to automatically detect new words.

CNNDeep LearningNLP

0 likes · 10 min read

Chinese New Word Discovery: From Traditional Unsupervised Methods to CNN‑Based Deep Learning

Alibaba Cloud Developer

Aug 8, 2019 · Artificial Intelligence

Alibaba VOS Innovations: Semi-supervised, Interactive & Unsupervised Segmentation

Video Object Segmentation (VOS) is essential for content creation, and Alibaba’s research outlines three main approaches—semi-supervised, interactive, and unsupervised—detailing their algorithms, challenges, evaluation metrics, recent breakthroughs, and future plans to improve accuracy in complex scenes.

Computer Visionaiinteractive

0 likes · 12 min read

Alibaba VOS Innovations: Semi-supervised, Interactive & Unsupervised Segmentation

Youku Technology

Jul 31, 2019 · Artificial Intelligence

Exploring the Three Key Research Directions in Video Object Segmentation

The article outlines video object segmentation (VOS), its importance for content creation, and details the three primary research avenues—semi‑supervised, interactive, and unsupervised—while reviewing benchmark metrics, algorithm categories, challenges, and recent advances from Alibaba’s MoKu Lab, including their competition results and future plans.

Computer Visionaiinteractive

0 likes · 14 min read

Exploring the Three Key Research Directions in Video Object Segmentation