Pith. sign in

REVIEW 9 cited by

Word Representations via Gaussian Embedding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1412.6623 v4 pith:TO4YV5GI submitted 2014-12-20 cs.CL cs.LG

classification cs.CLcs.LG
keywords representationsworddistributedembeddingembeddingsgaussianrelationshipsrepresentation
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Current work in lexical distributed representations maps each word to a point vector in low-dimensional space. Mapping instead to a density provides many interesting advantages, including better capturing uncertainty about a representation and its relationships, expressing asymmetries more naturally than dot product or cosine similarity, and enabling more expressive parameterization of decision boundaries. This paper advocates for density-based distributed embeddings and presents a method for learning representations in the space of Gaussian distributions. We compare performance on various word embedding benchmarks, investigate the ability of these embeddings to model entailment and other asymmetric relationships, and explore novel properties of the representation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. GRE-Diff: Gaussian Room Embeddings for Structured Layout Diffusion

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Modeling rooms as isotropic Gaussians and using them to initialize and guide diffusion yields controllable, editable polygonal floor plans that beat prior methods on RPLAN similarity and constraint metrics.

  2. Learning Probabilistic Embeddings for Unsupervised Action Segmentation

    cs.CV 2026-07 accept novelty 6.0 of 10

    Probabilistic Gaussian frame embeddings sampled before OT pseudo-labeling raise unsupervised action-segmentation MoF by up to 20.7% and F1 by 19% over deterministic baselines.

  3. TaxoBell: Gaussian Box Embeddings for Self-Supervised Taxonomy Expansion

    cs.CL 2026-01 conditional novelty 6.0 of 10

    TaxoBell, a Gaussian-box embedding model with symmetric and asymmetric energy losses, ranks parent concepts more accurately than seven taxonomy-expansion baselines on five benchmarks.

  4. Rethinking Word Similarity: Semantic Similarity through Classification Confusion

    cs.CL 2025-02 conditional novelty 6.0 of 10

    Word Confusion measures semantic similarity as classifier confusion between contextual embeddings, matching human judgments as well as or better than cosine similarity, and enables analyst-chosen feature dimensions.

  5. REGE: A Method for Incorporating Uncertainty in Graph Embeddings

    cs.LG 2024-12 conditional novelty 6.0 of 10

    REGE adds per-node uncertainty radii to graph embeddings and combines curriculum learning with conformal quantile regression to improve robustness to structural attacks.

  6. Using Images to Find Context-Independent Word Representations in Vector Space

    cs.CL 2024-11 reject novelty 6.0 of 10

    A method that represents each word by the concatenated autoencoder latent codes of images of its dictionary definition terms, evaluated on word similarity, categorization, and outlier detection.

  7. Native Hierarchical and Compositional Representations with Subspace Embeddings

    cs.LG 2025-08 conditional novelty 5.0 of 10

    Concepts are embedded as learned linear subspaces, so entailment becomes subspace inclusion and logical operations become intersection, sum, and orthogonal complement; the method claims SOTA on WordNet and surpasses b...

  8. Confidence Optimization for Probabilistic Encoding

    cs.LG 2025-07 conditional novelty 4.0 of 10

    A confidence-aware loss plus a negative L2 variance term gives a small boost to probabilistic encoding classifiers on TweetEval, but gains over the SPC baseline are modest and inconsistent on RoBERTa.

  9. Neural-Symbolic Reasoning over Knowledge Graphs: A Survey from a Query Perspective

    cs.AI 2024-11 conditional novelty 3.0 of 10

    A survey of knowledge graph reasoning methods organized by query type, covering symbolic, neural, neural-symbolic, and large language model approaches.

Pith tools