{"url":"/task/embeddings-evaluation","name":"Embeddings Evaluation","slug":"embeddings-evaluation","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":17,"papers_with_code":10,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/cannot","name":"CANNOT","full_name":"Compilation of ANnotated, Negation-Oriented Text-pairs","num_papers_in_archive":3},{"url":"/dataset/names-pairs-dataset","name":"Names pairs dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/word-embeddings","name":"Word Embeddings"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":10,"of":10,"tagged_in_all":17,"items":[{"url":"/paper/this-is-not-correct-negation-aware-evaluation","title":"This is not correct! Negation-aware Evaluation of Language Generation Systems","date":"2023-07-26","arxiv_id":"2307.13989","repositories_listed":2,"syntology":null},{"url":"/paper/collection-space-navigator-an-interactive","title":"Collection Space Navigator: An Interactive Visualization Interface for Multidimensional Datasets","date":"2023-05-11","arxiv_id":"2305.06809","repositories_listed":2,"syntology":null},{"url":"/paper/expert-concept-modeling-ground-truth","title":"Expert Concept-Modeling Ground Truth Construction for Word Embeddings Evaluation in Concept-Focused Domains","date":"2020-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/a-survey-of-word-embeddings-evaluation","title":"A Survey of Word Embeddings Evaluation Methods","date":"2018-01-21","arxiv_id":"1801.09536","repositories_listed":2,"syntology":null},{"url":"/paper/probabilistic-embeddings-for-frozen-vision","title":"Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models","date":"2025-05-08","arxiv_id":"2505.05163","repositories_listed":1,"syntology":null},{"url":"/paper/twlv-i-analysis-and-insights-from-holistic","title":"TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models","date":"2024-08-21","arxiv_id":"2408.11318","repositories_listed":1,"syntology":null},{"url":"/paper/embeddings-evaluation-using-a-novel-measure","title":"Embeddings Evaluation Using a Novel Measure of Semantic Similarity","date":"2022-01-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-meta-embeddings-what-works-and","title":"Benchmarking Meta-embeddings: What Works and What Does Not","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sart-similarity-analogies-and-relatedness-for","title":"SART - Similarity, Analogies, and Relatedness for Tatar Language: New Benchmark Datasets for Word Embeddings Evaluation","date":"2019-03-31","arxiv_id":"1904.00365","repositories_listed":1,"syntology":null},{"url":"/paper/the-limitations-of-cross-language-word","title":"The Limitations of Cross-language Word Embeddings Evaluation","date":"2018-06-06","arxiv_id":"1806.02253","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}