SOTAVerified

Natural Language Inference

Natural language inference (NLI) is the task of determining whether a "hypothesis" is true (entailment), false (contradiction), or undetermined (neutral) given a "premise".

Example:

| Premise | Label | Hypothesis | | --- | ---| --- | | A man inspects the uniform of a figure in some East Asian country. | contradiction | The man is sleeping. | | An older and younger man smiling. | neutral | Two men are smiling and laughing at the cats playing on the floor. | | A soccer game with multiple males playing. | entailment | Some men are playing a sport. |

Approaches used for NLI include earlier symbolic and statistical approaches to more recent deep learning approaches. Benchmark datasets used for NLI include SNLI, MultiNLI, SciTail, among others. You can get hands-on practice on the SNLI task by following this d2l.ai chapter.

Further readings:

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 251–300 of 1961 papers

TitleStatusHype
Calibration of Pre-trained TransformersCode1
Z-BERT-A: a zero-shot Pipeline for Unknown Intent detectionCode1
BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in BanglaCode1
ZeroGen: Efficient Zero-shot Learning via Dataset GenerationCode1
CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model BiasCode1
FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop DataCode1
KNOT: Knowledge Distillation using Optimal Transport for Solving NLP TasksCode1
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighterCode1
Cross-Modal BERT for Text-Audio Sentiment AnalysisCode1
Exploring the Benefits of Training Expert Language Models over Instruction TuningCode1
Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data GenerationCode1
FarsTail: A Persian Natural Language Inference DatasetCode1
Building Efficient Universal Classifiers with Natural Language InferenceCode1
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionCode1
Few-shot Learning with Multilingual Language ModelsCode1
Few-Shot Learning with Siamese Networks and Label TuningCode1
Can NLI Models Verify QA Systems' Predictions?Code1
Can Explanations Be Useful for Calibrating Black Box Models?Code1
Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?Code1
BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performanceCode1
Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERTCode1
A Broad-Coverage Challenge Corpus for Sentence Understanding through InferenceCode1
Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n ParametersCode1
New Protocols and Negative Results for Textual Entailment Data CollectionCode1
Chain of Natural Language Inference for Reducing Large Language Model Ungrounded HallucinationsCode1
FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim ExtractionCode1
Big Bird: Transformers for Longer SequencesCode1
CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From CharactersCode1
From Hero to Z\'eroe: A Benchmark of Low-Level Adversarial AttacksCode1
Charformer: Fast Character Transformers via Gradient-based Subword TokenizationCode1
ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin InformationCode1
BioELECTRA:Pretrained Biomedical text Encoder using DiscriminatorsCode1
Improving BERT Fine-Tuning via Self-Ensemble and Self-DistillationCode1
Citation-Enhanced Generation for LLM-based ChatbotsCode1
MABEL: Attenuating Gender Bias using Textual Entailment DataCode1
How to Train BERT with an Academic BudgetCode1
Pairwise Supervised Contrastive Learning of Sentence RepresentationsCode1
Compositional Explanations of NeuronsCode1
Cross-Lingual Word Embedding Refinement by _1 Norm OptimisationCode1
Improving Bot Response Contradiction Detection via Utterance RewritingCode1
Compositional Exemplars for In-context LearningCode1
Incorporating External Knowledge to Enhance Tabular ReasoningCode1
Compositional Evaluation on Japanese Textual Entailment and SimilarityCode1
Inducing Causal Structure for Interpretable Neural NetworksCode1
Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language InferenceCode1
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and EntailmentCode1
KagNet: Knowledge-Aware Graph Networks for Commonsense ReasoningCode1
Explaining Simple Natural Language InferenceCode0
Explanation Selection Using Unlabeled Data for Chain-of-Thought PromptingCode0
Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP ModelsCode0
Show:102550
← PrevPage 6 of 40Next →
All datasetsSNLIRTEMultiNLIQNLIANLI testWNLILiDiRusRCBTERRaCommitmentBankSciTailFarsTail

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1UnitedSynT5 (3B)% Test Accuracy94.7—Unverified
2UnitedSynT5 (335M)% Test Accuracy93.5—Unverified
3Neural Tree Indexers for Text Understanding% Test Accuracy93.1—Unverified
4EFL (Entailment as Few-shot Learner) + RoBERTa-large% Test Accuracy93.1—Unverified
5RoBERTa-large+Self-Explaining% Test Accuracy92.3—Unverified
6RoBERTa-large + self-explaining layer% Test Accuracy92.3—Unverified
7CA-MTL% Test Accuracy92.1—Unverified
8SemBERT% Test Accuracy91.9—Unverified
9MT-DNN-SMARTLARGEv0% Test Accuracy91.7—Unverified
10MT-DNN-SMART_100%ofTrainingDataDev Accuracy91.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Vega v2 6B (KD-based prompt transfer)Accuracy96—Unverified
2PaLM 540B (fine-tuned)Accuracy95.7—Unverified
3Turing NLR v5 XXL 5.4B (fine-tuned)Accuracy94.1—Unverified
4ST-MoE-32B 269B (fine-tuned)Accuracy93.5—Unverified
5DeBERTa-1.5BAccuracy93.2—Unverified
6MUPPET Roberta LargeAccuracy92.8—Unverified
7DeBERTaV3largeAccuracy92.7—Unverified
8T5-XXL 11B (fine-tuned)Accuracy92.5—Unverified
9T5-XXL 11BAccuracy92.5—Unverified
10ST-MoE-L 4.1B (fine-tuned)Accuracy92.1—Unverified
#ModelMetricClaimedVerifiedStatus
1UnitedSynT5 (3B)Matched92.6—Unverified
2Turing NLR v5 XXL 5.4B (fine-tuned)Matched92.6—Unverified
3T5-XXL 11B (fine-tuned)Matched92—Unverified
4T5Matched92—Unverified
5T5-11BMismatched91.7—Unverified
6T5-3BMatched91.4—Unverified
7ALBERTMatched91.3—Unverified
8Adv-RoBERTa ensembleMatched91.1—Unverified
9DeBERTa (large)Matched91.1—Unverified
10SMARTRoBERTaDev Matched91.1—Unverified