Context-Dependent Similarity
Attribute weighting and differential weighting, two major mechanisms for computing context-dependent similarity or dissimilarity measures are studied and compared. A dissimilarity measure based on subset size in the context is proposed and its metrization and application are given. It is also shown that while all attribute weighting dissimilarity measures are metrics differential weighting dissimilarity measures are usually non-metric.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeSimilar Papers 제목 키워드 기반
CoSimLex: A Resource for Evaluating Graded Word Similarity in Context
State of the art natural language processing tools are built on context-dependent word embeddings, but no direct method for evaluating these representations currently exists. Standard tasks and datasets for intrinsic eva…
Word EmbeddingsWord Sense DisambiguationWord SimilarityComparing in context: Improving cosine similarity measures with a metric tensor
Cosine similarity is a widely used measure of the relatedness of pre-trained word embeddings, trained on a language modeling goal. Datasets such as WordSim-353 and SimLex-999 rate how similar words are according to human…
Language ModelingLanguage ModellingWord EmbeddingsWord SimilarityGiCCS: A German in-Context Conversational Similarity Benchmark
The Semantic textual similarity (STS) task is commonly used to evaluate the semantic representations that language models (LMs) learn from texts, under the assumption that good-quality representations will yield accurate…
BenchmarkingSemantic Textual SimilaritySTSHuman Action Recognition Based on Context-Dependent Graph Kernels
Graphs are a powerful tool to model structured objects, but it is nontrivial to measure the similarity between two graphs. In this paper, we construct a two-graph model to represent human actions by recording the spatial…
Action RecognitionTemporal Action LocalizationContext-Dependent Affordance Computation in Vision-Language Models
We characterize the phenomenon of context-dependent affordance computation in vision-language models (VLMs). Our primary study uses Qwen3-VL-30B-A3B ($n = 3{,}213$ scene-context pairs from COCO-2017: 479 images under 7 a…