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

Showing 13511400 of 1961 papers

TitleStatusHype
Phrase-level Self-Attention Networks for Universal Sentence Encoding0
Cross-Pair Text Representations for Answer Sentence SelectionCode0
Hybrid Neural Attention for Agreement/Disagreement Inference in Online Debates0
Learning Corresponded Rationales for Text Matching0
Answering Science Exam Questions Using Query Rewriting with Background Knowledge0
Improving Natural Language Inference Using External Knowledge in the Science Questions Domain0
XNLI: Evaluating Cross-lingual Sentence RepresentationsCode0
AWE: Asymmetric Word Embedding for Textual Entailment0
Transforming Question Answering Datasets Into Natural Language Inference DatasetsCode1
Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag RepresentationsCode0
Cell-aware Stacked LSTMs for Modeling Sentences0
UKP-Athene: Multi-Sentence Textual Entailment for Claim VerificationCode0
DeFactoNLP: Fact Verification using Entity Recognition, TFIDF Vector Comparison and Decomposable AttentionCode0
What can we learn from Semantic Tagging?0
Bridging Knowledge Gaps in Neural Entailment via Symbolic Models0
Sentence Embeddings in NLI with Iterative Refinement EncodersCode0
Adversarially Regularising Neural NLI Models to Integrate Logical Background KnowledgeCode0
Dynamic Self-Attention : Computing Attention over Words Dynamically for Sentence EmbeddingCode1
Lessons from Natural Language Inference in the Clinical DomainCode0
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference0
REGMAPR - Text Matching Made Easy0
Interpreting Recurrent and Attention-Based Neural Models: a Case Study on Natural Language Inference0
TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim VerificationCode0
WARP-Text: a Web-Based Tool for Annotating Relationships between Pairs of TextsCode0
Scoring and Classifying Implicit Positive Interpretations: A Challenge of Class ImbalanceCode0
Embedding WordNet Knowledge for Textual Entailment0
Adopting the Word-Pair-Dependency-Triplets with Individual Comparison for Natural Language Inference0
Towards Coreference for Literary Text: Analyzing Domain-Specific Phenomena0
Multiway Attention Networks for Modeling Sentence PairsCode0
Domain Adaptation for Disease Phrase Matching with Adversarial Networks0
Unsupervised Source Hierarchies for Low-Resource Neural Machine Translation0
Connecting Supervised and Unsupervised Sentence Embeddings0
Natural Language Inference with Definition Embedding Considering Context On the Fly0
BioAMA: Towards an End to End BioMedical Question Answering System0
Discovering Implicit Knowledge with Unary RelationsCode0
Variational Inference and Deep Generative Models0
Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search0
Jack the Reader -- A Machine Reading FrameworkCode0
Enhancing Sentence Embedding with Generalized PoolingCode0
Jack the Reader - A Machine Reading FrameworkCode1
The Natural Language Decathlon: Multitask Learning as Question AnsweringCode1
GLoMo: Unsupervisedly Learned Relational Graphs as Transferable RepresentationsCode0
Grounded Textual EntailmentCode0
Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question AnsweringCode0
Improving Language Understanding by Generative Pre-TrainingCode1
What Knowledge is Needed to Solve the RTE5 Textual Entailment Challenge?0
Stress Test Evaluation for Natural Language InferenceCode0
Predicting Human Metaphor Paraphrase Judgments with Deep Neural Networks0
Literal, Metphorical or Both? Detecting Metaphoricity in Isolated Adjective-Noun Phrases0
GKR: the Graphical Knowledge Representation for semantic parsing0
Show:102550
← PrevPage 28 of 40Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1UnitedSynT5 (3B)% Test Accuracy94.7Unverified
2UnitedSynT5 (335M)% Test Accuracy93.5Unverified
3EFL (Entailment as Few-shot Learner) + RoBERTa-large% Test Accuracy93.1Unverified
4Neural Tree Indexers for Text Understanding% Test Accuracy93.1Unverified
5RoBERTa-large+Self-Explaining% Test Accuracy92.3Unverified
6RoBERTa-large + self-explaining layer% Test Accuracy92.3Unverified
7CA-MTL% Test Accuracy92.1Unverified
8SemBERT% Test Accuracy91.9Unverified
9MT-DNN-SMARTLARGEv0% Test Accuracy91.7Unverified
10MT-DNN-SMART_100%ofTrainingDataDev Accuracy91.6Unverified
#ModelMetricClaimedVerifiedStatus
1Vega v2 6B (KD-based prompt transfer)Accuracy96Unverified
2PaLM 540B (fine-tuned)Accuracy95.7Unverified
3Turing NLR v5 XXL 5.4B (fine-tuned)Accuracy94.1Unverified
4ST-MoE-32B 269B (fine-tuned)Accuracy93.5Unverified
5DeBERTa-1.5BAccuracy93.2Unverified
6MUPPET Roberta LargeAccuracy92.8Unverified
7DeBERTaV3largeAccuracy92.7Unverified
8T5-XXL 11BAccuracy92.5Unverified
9T5-XXL 11B (fine-tuned)Accuracy92.5Unverified
10ST-MoE-L 4.1B (fine-tuned)Accuracy92.1Unverified
#ModelMetricClaimedVerifiedStatus
1UnitedSynT5 (3B)Matched92.6Unverified
2Turing NLR v5 XXL 5.4B (fine-tuned)Matched92.6Unverified
3T5-XXL 11B (fine-tuned)Matched92Unverified
4T5Matched92Unverified
5T5-11BMismatched91.7Unverified
6T5-3BMatched91.4Unverified
7ALBERTMatched91.3Unverified
8DeBERTa (large)Matched91.1Unverified
9Adv-RoBERTa ensembleMatched91.1Unverified
10SMARTRoBERTaDev Matched91.1Unverified