AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Incrementally Learning the Hierarchical Softmax Function for Neural Language Models

Hao Peng, Jianxin Li, Yangqiu Song, Yaopeng Liu

AAAI 2017 · Architectures and efficiency › RNNs and normalization · approach: Non-autoregressive translation · 79 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
handle Huffman tree change with prefix matching instead of reserving old tree (ablation)incremental CBOW · vector MSE vs global trainingMSE: 7.84 × 10−3 -> 6.66 × 10−3Improved
handle Huffman tree change with prefix matching instead of reserving old tree (ablation)incremental Skip-gram · vector MSE vs global trainingMSE: 7.83 × 10−3 -> 6.68 × 10−3Improved
incremental update instead of full retrainingSkip-gram · training timespeedup: up to 30 timesImproved
incremental update instead of full retrainingCBOW · training timespeedup: up to 10 timesImproved
incremental update vs global retrainingword vectors · word similarity benchmarksSpearman correlationNo clear effect
incremental update vs global retrainingword vectors · dependency parsingUAS/LASNo clear effect
reserve old tree instead of updating it (ablation)incremental training · dependency parsingUAS/LASHurt
increase update corpus sizeincremental training · training speedupspeedupHurt

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