AI Paper Atlas

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

P-SIF: Document Embeddings Using Partition Averaging

Vivek Gupta, Ankit Saw, Pegah Nokhiz, Praneeth Netrapalli, Piyush Rai, Partha Talukdar

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 26 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 topic partitioning and concatenation to SIF weighted averagingSIF document embeddings · 20NewsGroupaccuracy: 82.3 -> 85.4Improved
Add topic partitioning and concatenation to SIF weighted averagingSIF document embeddings · Reuters-21578F1: 76.78 -> 82.41Improved
Initialize word vectors with Doc2VecC (ablation)P-SIF · 20NewsGroupaccuracy: 85.4 -> 86.0Improved
Initialize word vectors with Doc2VecC (ablation)P-SIF · Reuters-21578F1: 82.41 -> 82.87Improved
Use GMM overlapping clustering instead of sparse dictionary learning (ablation)P-SIF · Some STS tasks with short, single-sentence textsPearson's rImproved
Use sparse dictionary learning instead of GMM overlapping clustering (ablation)P-SIF · 20NewsGroup and Reuters classificationF1: ~1.5%Improved
Weight each word embedding by its learned dictionary coefficient (ablation)P-SIF word-topic vectors · Document embedding tasksperformanceImproved
Increase word-vector dimensions from 200 to 500 (ablation)SIF and P-SIF · 20NewsGroupaccuracy: <0.4%No clear effect
Increase word-vector dimensions beyond 500 (ablation)SIF and P-SIF · Document classificationperformanceNo clear effect
Use 20 partitions with Doc2VecC-initialized vectors instead of 40 (ablation)P-SIF · 20NewsGroupaccuracy: 40 partitions; 20 partitionsImproved

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