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
Signed reviews
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.
Forward citations
Cited by 9 Pith papers
-
GRE-Diff: Gaussian Room Embeddings for Structured Layout Diffusion
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.
-
Learning Probabilistic Embeddings for Unsupervised Action Segmentation
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.
-
TaxoBell: Gaussian Box Embeddings for Self-Supervised Taxonomy Expansion
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.
-
Rethinking Word Similarity: Semantic Similarity through Classification Confusion
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.
-
REGE: A Method for Incorporating Uncertainty in Graph Embeddings
REGE adds per-node uncertainty radii to graph embeddings and combines curriculum learning with conformal quantile regression to improve robustness to structural attacks.
-
Using Images to Find Context-Independent Word Representations in Vector Space
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.
-
Native Hierarchical and Compositional Representations with Subspace Embeddings
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...
-
Confidence Optimization for Probabilistic Encoding
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.
-
Neural-Symbolic Reasoning over Knowledge Graphs: A Survey from a Query Perspective
A survey of knowledge graph reasoning methods organized by query type, covering symbolic, neural, neural-symbolic, and large language model approaches.
Discussion (0). Continue with ORCID to comment.