AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information

Shaosheng Cao, Wei Lu, Jun Zhou, Xiaolong Li

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 125 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
represent words by stroke n-grams (cw2vec) vs component-based JWEChinese word embeddings · word analogy 3CosAddaccuracy: 74.2 -> 78.1Improved
cw2vec vs JWEChinese word embeddings · BosonNLP NERF1: 67.9 -> 71.7Improved
cw2vec vs best baselineChinese word embeddings · Fudan text classificationaccuracy: 94.3 -> 95.3Improved
cw2vec vs JWEChinese word embeddings · wordsim-296Spearman rho x100: 52.7 -> 52.7No clear effect
cw2vec vs CWEChinese word embeddings · wordsim-240Spearman rho x100: 50.0 -> 50.4Improved
add character information (CWE vs skip-gram)word2vec · word analogy 3CosAddaccuracy: 58.3 -> 68.5Improved
use pixel-based glyph features (GWE vs skip-gram)word2vec · word analogy 3CosAddaccuracy: 58.3 -> 50.8Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy