{"url":"/dataset/sick","name":"SICK","full_name":"Sentences Involving Compositional Knowledge","description_markdown":"The **Sentences Involving Compositional Knowledge** (**SICK**) dataset is a dataset for compositional distributional semantics. It includes a large number of sentence pairs that are rich in the lexical, syntactic and semantic phenomena. Each pair of sentences is annotated in two dimensions: relatedness and entailment. The relatedness score ranges from 1 to 5, and Pearson’s r is used for evaluation; the entailment relation is categorical, consisting of entailment, contradiction, and neutral. There are 4439 pairs in the train split, 495 in the trial split used for development and 4906 in the test split. The sentence pairs are generated from image and video caption datasets before being paired up using some algorithm.\r\n\r\nSource: [Multi-Label Transfer Learning for Multi-Relational Semantic Similarity](https://arxiv.org/abs/1805.12501)\r\nImage Source: [https://www.researchgate.net/figure/Example-of-SICK-dataset-sentence-expansion-process-14_fig1_344863619](https://www.researchgate.net/figure/Example-of-SICK-dataset-sentence-expansion-process-14_fig1_344863619)","description_withheld":null,"homepage":"http://marcobaroni.org/composes/sick.html","introduced_date":"2014-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-sick-cure-for-the-evaluation-of","title":"A SICK cure for the evaluation of compositional distributional semantic models","first_author":"Marco Marelli","url":null},"license":{"name":"CC BY-NC-SA 3.0","url":"http://marcobaroni.org/composes/sick.html#:~:text=Creative%20Commons%20Attribution-NonCommercial-ShareAlike%20license"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Semantic Textual Similarity","url":"/task/semantic-textual-similarity","datasets_with_task":"/datasets/task/semantic-textual-similarity"},{"name":"Semantic Similarity","url":"/task/semantic-similarity","datasets_with_task":"/datasets/task/semantic-similarity"},{"name":"Tabular Data Generation","url":"/task/tabular-data-generation","datasets_with_task":"/datasets/task/tabular-data-generation"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["SICK","SICK-R"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/RobZamp/sick","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/sick","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":348,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-textual-similarity-on-sick","task":"Semantic Textual Similarity","dataset_variant":"SICK","rows":22,"metrics":["Spearman Correlation"],"first_row_in_archive_order":{"model":"PromCSE-RoBERTa-large (0.355B)","paper":"/paper/deep-continuous-prompt-for-contrastive-1","metrics":{"Spearman Correlation":"0.8243"},"code_links":[{"title":"yjiangcm/promcse","url":"https://github.com/yjiangcm/promcse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/tabular-data-generation-on-sick","task":"Tabular Data Generation","dataset_variant":"SICK","rows":6,"metrics":["DT Accuracy","LR Accuracy","Parameters(M)","RF Accuracy"],"first_row_in_archive_order":{"model":"GReaT","paper":"/paper/language-models-are-realistic-tabular-data","metrics":{"DT Accuracy":"97.72","LR Accuracy":"97.72","Parameters(M)":"355","RF Accuracy":"98.3"},"code_links":[{"title":"kathrinse/be_great","url":"https://github.com/kathrinse/be_great"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-similarity-on-sick","task":"Semantic Similarity","dataset_variant":"SICK","rows":5,"metrics":["MSE","Pearson Correlation","Spearman Correlation"],"first_row_in_archive_order":{"model":"Dependency Tree-LSTM (Tai et al., 2015)","paper":"/paper/improved-semantic-representations-from-tree","metrics":{"MSE":"0.2532","Pearson Correlation":"0.8676","Spearman Correlation":"0.8083"},"code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/tree_lstm"},{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/tree_lstm"},{"title":"tensorflow/fold","url":"https://github.com/tensorflow/fold"},{"title":"stanfordnlp/treelstm","url":"https://github.com/stanfordnlp/treelstm"},{"title":"dasguptar/treelstm.pytorch","url":"https://github.com/dasguptar/treelstm.pytorch"},{"title":"ttpro1995/TreeLSTMSentiment","url":"https://github.com/ttpro1995/TreeLSTMSentiment"},{"title":"inyukwo1/tree-lstm","url":"https://github.com/inyukwo1/tree-lstm"},{"title":"munashe5/SemanticTreeLSTM","url":"https://github.com/munashe5/SemanticTreeLSTM"},{"title":"tomekkorbak/treehopper","url":"https://github.com/tomekkorbak/treehopper"},{"title":"EmilReinert/DeepLearningPipelines","url":"https://github.com/EmilReinert/DeepLearningPipelines"},{"title":"rohitguptacs/ReVal","url":"https://github.com/rohitguptacs/ReVal"},{"title":"vastsak/tree_structured_gru","url":"https://github.com/vastsak/tree_structured_gru"},{"title":"zxk19981227/LSTM-SST","url":"https://github.com/zxk19981227/LSTM-SST"},{"title":"Mind23-2/MindCode-17","url":"https://github.com/Mind23-2/MindCode-17"},{"title":"jayanti-prasad/TreeLSTM","url":"https://github.com/jayanti-prasad/TreeLSTM"},{"title":"Vivswan/Sentiment-Analysis-TreeLSTM","url":"https://github.com/Vivswan/Sentiment-Analysis-TreeLSTM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-textual-similarity-on-sick-r-1","task":"Semantic Textual Similarity","dataset_variant":"SICK-R","rows":2,"metrics":["Spearman Correlation"],"first_row_in_archive_order":{"model":"AnglE-LLaMA-7B","paper":"/paper/angle-optimized-text-embeddings","metrics":{"Spearman Correlation":"0.8094"},"code_links":[{"title":"SeanLee97/AnglE","url":"https://github.com/SeanLee97/AnglE"},{"title":"4ai/bellm","url":"https://github.com/4ai/bellm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/natural-language-inference-on-sick","task":"Natural Language Inference","dataset_variant":"SICK","rows":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"NeuralLog","paper":"/paper/neurallog-natural-language-inference-with","metrics":{"1:1 Accuracy":"0.903"},"code_links":[{"title":"eric11eca/NeuralLog","url":"https://github.com/eric11eca/NeuralLog"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/tabular-data-generation-using-binary","title":"Tabular Data Generation using Binary Diffusion","date":"2024-09-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":10,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rematch-robust-and-efficient-matching-of","title":"Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similarity","date":"2024-04-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/angle-optimized-text-embeddings","title":"AnglE-optimized Text Embeddings","date":"2023-09-22","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/scaling-sentence-embeddings-with-large","title":"Scaling Sentence Embeddings with Large Language Models","date":"2023-07-31","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/language-models-are-realistic-tabular-data","title":"Language Models are Realistic Tabular Data Generators","date":"2022-10-12","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-continuous-prompt-for-contrastive-1","title":"Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning","date":"2022-03-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/trans-encoder-unsupervised-sentence-pair","title":"Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","date":"2021-09-27","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/neurallog-natural-language-inference-with","title":"NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning","date":"2021-05-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/simcse-simple-contrastive-learning-of","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","date":"2021-04-18","rows_on_this_dataset":1,"code_links":23,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":30,"samples_ran":17,"samples_unverified":13,"pointer_only_for_licence":19,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fast-effective-and-self-supervised","title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","date":"2021-04-16","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/generating-datasets-with-pretrained-language","title":"Generating Datasets with Pretrained Language Models","date":"2021-04-15","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/on-the-sentence-embeddings-from-pre-trained","title":"On the Sentence Embeddings from Pre-trained Language Models","date":"2020-11-02","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/an-unsupervised-sentence-embedding-method","title":"An Unsupervised Sentence Embedding Method by Mutual Information Maximization","date":"2020-09-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sentence-bert-sentence-embeddings-using","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","date":"2019-08-27","rows_on_this_dataset":5,"code_links":64,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":58,"samples_ran":20,"samples_unverified":38,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/modeling-tabular-data-using-conditional-gan","title":"Modeling Tabular data using Conditional GAN","date":"2019-07-01","rows_on_this_dataset":3,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-vector-representation-for-documents","title":"Efficient Vector Representation for Documents through Corruption","date":"2017-07-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/skip-thought-vectors","title":"Skip-Thought Vectors","date":"2015-06-22","rows_on_this_dataset":1,"code_links":16,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improved-semantic-representations-from-tree","title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","date":"2015-02-28","rows_on_this_dataset":3,"code_links":16,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":6,"samples_unverified":9,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":12,"samples_harvested":142,"samples_ran":62,"samples_unverified":80,"pointer_only_for_licence":40,"papers_with_no_sample_that_ran":5,"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."}