3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in embeddings-evaluation-15
No benchmarks available.
Use these libraries to find embeddings-evaluation-15 models and implementations
No subtasks available.
This paper designed a rule-based sentence negation tool and used it to create the CANNOT negation evaluation dataset, and fine-tuned a sentence transformer and an evaluation metric to improve their negation sensitivity.
We introduce the Collection Space Navigator (CSN), a browser-based visualization tool to explore, research, and curate large collections of visual digital artifacts that are associated with multidimensional data, such as vector embeddings or tables of metadata. Media objects such as images are often encoded as numerical vectors, based on metadata or using machine learning embeddings. Yet it remains a challenge to explore, analyze, and understand the resulting multidimensional spaces. Dimensionality reduction techniques such as t-SNE or UMAP often serve to project high-dimensional data into low dimensional visualizations, but require interpretation themselves given their typically abstract dimensions. The Collection Space Navigator provides a customizable interface that combines two-dimensional projections with an array of configurable multifunctional filters and navigation controls. The user is able to view and investigate collections by zooming and scaling, transforming between projections, and filtering dimensions via range sliders and text filters. Insights gained through these interactions can be used to augment original data via easy to use export capabilities. This paper comes with a functional online demo showcasing a large digitized collection of classical Western art. Users can reconfigure the interface to fit their own data and research needs, including projections and filter controls. This open source tool is intended to be applicable in a broad range of use cases, types of collections and across diverse disciplines.
An extensive overview of the field of word embeddings evaluation is presented, highlighting main problems and proposing a typology of approaches to evaluation, summarizing 16 intrinsic methods and 12 extrinsic methods.
A novel, domain expert-controlled, replicable procedure for the construction of concept-modeling ground truths with the aim of evaluating the application of word embeddings in concept-focused textual domains, where a generic ontology does not provide enough information.
Three datasets are presented: Similarity and Relatedness datasets that consist of human scored word pairs and can be used to evaluate semantic models; and Analogies dataset that comprises analogy questions and allows to explore semantic, syntactic, and morphological aspects of language modeling.
It is concluded that the use of human references as ground truth for cross-language word embeddings is not proper unless one does not understand how do native speakers process semantics in their cognition.
Experimental results show that HSS outperforms state-of-the-art measures for measuring semantic similarity in taxonomy on a benchmark intrinsic evaluation and the embedding selected through TaxoVec achieves a clear victory against embeddings selected by the competing measures on benchmark NLP tasks.
Adding a benchmark result helps the community track progress.