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 851–900 of 1961 papers

TitleStatusHype
Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference—0
Scalar Adjective Identification and Multilingual Ranking—0
Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks—0
Switching Contexts: Transportability Measures for NLPCode0
Evaluating Attribution in Dialogue Systems: The BEGIN BenchmarkCode1
Entailment as Few-Shot LearnerCode1
PanGu-α: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel ComputationCode1
Finding Fuzziness in Neural Network Models of Language ProcessingCode0
SimCSE: Simple Contrastive Learning of Sentence EmbeddingsCode2
Can NLI Models Verify QA Systems' Predictions?Code1
Distributed NLI: Learning to Predict Human Opinion Distributions for Language ReasoningCode1
Q^2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question AnsweringCode1
Supervising Model Attention with Human Explanations for Robust Natural Language InferenceCode0
How to Train BERT with an Academic BudgetCode1
Does Putting a Linguist in the Loop Improve NLU Data Collection?—0
"I'm Not Mad": Commonsense Implications of Negation and Contradiction—0
Cross-Lingual Word Embedding Refinement by _1 Norm OptimisationCode1
Unsupervised Learning of Explainable Parse Trees for Improved GeneralisationCode0
NLI Data Sanity Check: Assessing the Effect of Data Corruption on Model PerformanceCode0
Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt CollectionsCode1
Incorporating External Knowledge to Enhance Tabular ReasoningCode1
Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group MasksCode0
BreakingBERT@IITK at SemEval-2021 Task 9 : Statement Verification and Evidence Finding with TablesCode0
Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy ReasoningCode0
Cross-Lingual Transfer with MAML on Trees—0
How Fast can BERT Learn Simple Natural Language Inference?—0
SICK-NL: A Dataset for Dutch Natural Language InferenceCode0
A Simple Three-Step Approach for the Automatic Detection of Exaggerated Statements in Health Science News—0
Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference—0
You Can Do Better! If You Elaborate the Reason When Making Prediction—0
Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2—0
Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning—0
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing—0
SILT: Efficient transformer training for inter-lingual inferenceCode0
Robustly Optimized and Distilled Training for Natural Language Understanding—0
Get Your Vitamin C! Robust Fact Verification with Contrastive EvidenceCode1
Meta-Learning with MAML on Trees—0
Overcoming Poor Word Embeddings with Word Definitions—0
PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen DomainsCode1
Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n ParametersCode1
Have Attention Heads in BERT Learned Constituency Grammar?—0
Capturing Label Distribution: A Case Study in NLI—0
Language Models for Lexical Inference in ContextCode0
Nyströmformer: A Nyström-Based Algorithm for Approximating Self-AttentionCode1
A Note on Argumentative Topology: Circularity and Syllogisms as Unsolved Problems—0
Does Putting a Linguist in the Loop Improve NLU Data Collection?—0
LSOIE: A Large-Scale Dataset for Supervised Open Information ExtractionCode1
Muppet: Massive Multi-task Representations with Pre-FinetuningCode0
Exploring Transitivity in Neural NLI Models through VeridicalityCode0
Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks—0
Show:102550
← PrevPage 18 of 40Next →
All datasetsSNLIRTEMultiNLIQNLIANLI testWNLILiDiRusRCBTERRaCommitmentBankSciTailFarsTail

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1UnitedSynT5 (3B)% Test Accuracy94.7—Unverified
2UnitedSynT5 (335M)% Test Accuracy93.5—Unverified
3EFL (Entailment as Few-shot Learner) + RoBERTa-large% Test Accuracy93.1—Unverified
4Neural Tree Indexers for Text Understanding% 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 11BAccuracy92.5—Unverified
9T5-XXL 11B (fine-tuned)Accuracy92.5—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
8DeBERTa (large)Matched91.1—Unverified
9Adv-RoBERTa ensembleMatched91.1—Unverified
10SMARTRoBERTaDev Matched91.1—Unverified