SICK

Overview edit

Variants: SICK, SICK-R

Associated Benchmarks

This dataset is used in 4 benchmarks:

• Natural Language Inference - Metrics: 1:1 Accuracy
• Semantic Textual Similarity - Metrics: Spearman Correlation
• Semantic Similarity - Metrics: MSE, Pearson Correlation, Spearman Correlation
• Tabular Data Generation - Metrics: DT Accuracy, LR Accuracy, Parameters(M), RF Accuracy

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• Tabular Data Generation using Binary Diffusion (2024) -
• Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similarity (2024) -
• Scaling Sentence Embeddings with Large Language Models (2023) -
• Language Models are Realistic Tabular Data Generators (2022) -
• Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning (2022) -
• Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations (2021) -
• NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning (2021) -
• SimCSE: Simple Contrastive Learning of Sentence Embeddings (2021) -
• Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders (2021) -
• Generating Datasets with Pretrained Language Models (2021) -
• On the Sentence Embeddings from Pre-trained Language Models (2020) -
• An Unsupervised Sentence Embedding Method by Mutual Information Maximization (2020) -
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (2019) -
• Modeling Tabular data using Conditional GAN (2019) -
• Efficient Vector Representation for Documents through Corruption (2017) -
• Skip-Thought Vectors (2015) -
• Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks (2015) -