AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Understanding Composition of Word Embeddings via Tensor Decomposition

Abraham Frandsen, Rong Ge

ICLR 2019 · Architectures and efficiency › RNNs and normalization · approach: Learned embeddings for retrieval · 6 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
Use weighted tensor composition instead of simple addition (ablation)Adjective-noun phrase embeddings · Adjective-noun phrase similaritySpearman and Pearson correlation: rw: .446, .438 -> .460, .465; glove: .357, .336 -> .368, .347; cbow Spearman: .471 -> .474; cbow Pearson: .452 -> .471Improved
Add tensor correction to SIF phrase embeddings (ablation)Adjective-noun phrase embeddings · Adjective-noun phrase similaritySpearman and Pearson correlation: rw: .482, .477 -> .482, .481; glove: .429, .434 -> .433, .437; cbow: .489, .482 -> .492, .484Improved
Use unweighted tensor composition rather than simple addition (ablation)Phrase embeddings · Phrase similarity before tuning tensor weightCorrelation with human ratingsHurt
Use weighted tensor correction with tuned alpha (ablation)Verb-object phrase embeddings · Verb-object phrase similaritySpearman and Pearson correlation: GloVe Spearman: .401 -> .410; GloVe Pearson: .404 -> .420; CBOW Pearson: .415 -> .422; RAND-WALK weighted2: .392, .387 vMixed
Add tensor correction to SIF phrase embeddings (ablation)Verb-object phrase embeddings · Verb-object phrase similaritySpearman and Pearson correlation: GloVe: .387, .380 -> .411, .409; RAND-WALK: .378, .351 -> .378, .363; CBOW: .404, .404 -> .420, .417Mixed
Add adjective-noun tensor corrections to review embeddings (ablation)Movie-review sentiment classifier · Pang and Lee movie reviewsTest accuracy: 0.741 (0.018) -> 0.759 (0.025)No clear effect
Add adjective-noun tensor corrections to review embeddings (ablation)Movie-review sentiment classifier · Large Movie ReviewTest accuracy: 0.793 -> 0.794No clear effect
Use tensor rather than additive phrase composition (ablation)Qualitative retrieval of phrase-related words · Adjective-noun and verb-object phrase retrievalQualitative relevanceMixed

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