{"url":"/dataset/sild","name":"SILD","full_name":"Survey Item Linking Dataset","description_markdown":"This dataset contains a collection of texts from publications from a broad range of social science domains (e.g., economics, politics, psychology, etc.). The texts are annotated with labels for [Survey Item Linking (SIL)](https://github.com/e-tornike/SIL), an [Entity Linking (EL)](https://en.wikipedia.org/wiki/Entity_linking) task. SIL is divided into two sub-tasks: Mention Detection (MD), a binary text classification task, and Entity Disambiguation (ED), a sentence similarity task. Sentences that mention survey items are labeled with the IDs of entities from a knowledge base ([GSIM](https://github.com/e-tornike/SIL/tree/main/data/gsim)). SILD contains 20,454 sentences in English and German from 100 publications.","description_withheld":null,"homepage":"https://github.com/e-tornike/SIL","introduced_date":"2024-06-14","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Variable Detection","url":"/task/variable-detection","datasets_with_task":"/datasets/task/variable-detection"},{"name":"Variable Disambiguation","url":"/task/variable-disambiguation","datasets_with_task":"/datasets/task/variable-disambiguation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"German","url":"/datasets/language/german"}],"variants":["SILD"],"data_loaders":[],"num_papers_in_archive":0,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}