QNLI

Question-answering NLI

Dataset Information
Modalities
Texts
Languages
English
Introduced
2019
License
CC BY-SA 4.0
Homepage
Official Website
Contents

Overview

The QNLI (Question-answering NLI) dataset is a Natural Language Inference dataset automatically derived from the Stanford Question Answering Dataset v1.1 (SQuAD). SQuAD v1.1 consists of question-paragraph pairs, where one of the sentences in the paragraph (drawn from Wikipedia) contains the answer to the corresponding question (written by an annotator). The dataset was converted into sentence pair classification by forming a pair between each question and each sentence in the corresponding context, and filtering out pairs with low lexical overlap between the question and the context sentence. The task is to determine whether the context sentence contains the answer to the question. This modified version of the original task removes the requirement that the model select the exact answer, but also removes the simplifying assumptions that the answer is always present in the input and that lexical overlap is a reliable cue. The QNLI dataset is part of GLUE benchmark.

Source: https://arxiv.org/pdf/1804.07461.pdf

Variants: QNLI, QNLI (8 training examples per class), QNLI Dev

Associated Benchmarks

This dataset is used in 3 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Data-free Knowledge Distillation GOLD (T5-base) GOLD: Generalized Knowledge Distillation via … 2024-03-28
Data-free Knowledge Distillation Prompt2Model (T5-base) Prompt2Model: Generating Deployable Models from … 2023-08-23
Natural Language Inference LM-CPPF RoBERTa-base LM-CPPF: Paraphrasing-Guided Data Augmentation for … 2023-05-29
Model Compression MobileBERT + 1bit-1dim model compression using DKM R2 Loss: Range Restriction Loss … 2023-03-14
Model Compression MobileBERT + 2bit-1dim model compression using DKM R2 Loss: Range Restriction Loss … 2023-03-14
Data-free Knowledge Distillation ProGen (T5-base) ProGen: Progressive Zero-shot Dataset Generation … 2022-10-22
Natural Language Inference RoBERTa-large 355M (MLP quantized vector-wise, fine-tuned) LLM.int8(): 8-bit Matrix Multiplication for … 2022-08-15
Natural Language Inference ASA + BERT-base Adversarial Self-Attention for Language Understanding 2022-06-25
Natural Language Inference ASA + RoBERTa Adversarial Self-Attention for Language Understanding 2022-06-25
Data-free Knowledge Distillation ZeroGen (T5-base) ZeroGen: Efficient Zero-shot Learning via … 2022-02-16
Natural Language Inference data2vec data2vec: A General Framework for … 2022-02-07
Natural Language Inference DeBERTaV3large DeBERTaV3: Improving DeBERTa using ELECTRA-Style … 2021-11-18
Natural Language Inference Charformer-Tall Charformer: Fast Character Transformers via … 2021-06-23
Natural Language Inference FNet-Large FNet: Mixing Tokens with Fourier … 2021-05-09
Natural Language Inference RoBERTa-large 355M + Entailment as Few-shot Learner Entailment as Few-Shot Learner 2021-04-29
Natural Language Inference 24hBERT How to Train BERT with … 2021-04-15
Natural Language Inference Nyströmformer Nyströmformer: A Nyström-Based Algorithm for … 2021-02-07
Natural Language Inference MLM+ subs+ del-span CLEAR: Contrastive Learning for Sentence … 2020-12-31
Natural Language Inference RealFormer RealFormer: Transformer Likes Residual Attention 2020-12-21
Natural Language Inference PSQ (Chen et al., 2020) A Statistical Framework for Low-bitwidth … 2020-10-27

Research Papers

Recent papers with results on this dataset:

External Links: