AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Training and Evaluating Improved Dependency-Based Word Embeddings

Chen Li, Jianxin Li, Yangqiu Song, Ziwei Lin

AAAI 2018 · Architectures and efficiency › RNNs and normalization · approach: Learned embeddings for retrieval · 14 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
add multi-order dependency context with learned dependency weights and vectors to Skip-Gram NSSG&NS · SIMLEX-999Spearman: 0.3559 -> 0.3686Improved
add multi-order dependency context to Skip-Gram NSSG&NS · CoNLL-2003 NERF1: 82.44 -> 85.14Improved
add multi-order dependency context to CBOW HSCBOW&HS · CoNLL-2003 NERF1: 80.67 -> 82.87Improved
add dependency vectors to input in addition to dependency weights (SG) (ablation)SGDeps&NS · CoNLL-2003 NERF1: 83.89 -> 85.14Improved
add dependency vectors to input in addition to weights (CBOW) (ablation)CBOWDeps&HS · WS-353-SIMSpearman: 0.7094 -> 0.7234Improved
add dependency vectors to input in addition to weights (SG) (ablation)SGDeps&NS · RG-65Spearman: 0.7267 -> 0.7348Improved
multi-order SG Deps vs first-order Deps (Levy & Goldberg)SGDeps&NS · RWSpearman: 0.3994 -> 0.3964No clear effect
replace Deps/EXT dependency embeddings with proposed on coreferenceSGDeps&NS · CoNLL-2012 coreferenceMUC F1: 70.8 -> 71.3Improved
add dependency context to CBOW HSCBOW&HS · CoNLL-2012 coreferenceMUC F1: 69.2 -> 69.8Mixed

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