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 16511700 of 1961 papers

TitleStatusHype
Corpora for Learning the Mutual Relationship between Semantic Relatedness and Textual Entailment0
Why and How to Pay Different Attention to Phrase Alignments of Different Intensities0
Probabilistic Reasoning via Deep Learning: Neural Association Models0
Sentence Pair Scoring: Towards Unified Framework for Text ComprehensionCode0
Attention-Based Convolutional Neural Network for Machine Comprehension0
From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label ClassificationCode0
Long Short-Term Memory-Networks for Machine ReadingCode0
Learning to Make Inferences in a Semantic Parsing Task0
Discrete-State Variational Autoencoders for Joint Discovery and Factorization of RelationsCode0
An Empirical Analysis of Formality in Online Communication0
Learning Natural Language Inference with LSTMCode0
Natural Language Inference by Tree-Based Convolution and Heuristic Matching0
ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence PairsCode0
Enacting textual entailment and ontologies for automated essay grading in chemical domain0
Semi-Automatic Construction of a Textual Entailment Dataset: Selecting Candidates with Vector Space Models0
Corpus annotation with a linguistic analysis of the associations between event mentions and spatial expressions0
Reasoning about Entailment with Neural AttentionCode0
Estimation of Discourse Segmentation Labels from Crowd Data0
Where Was Alexander the Great in 325 BC? Toward Understanding History Text with a World Model0
A Strong Lexical Matching Method for the Machine Comprehension Test0
Recognizing Textual Entailment Using Probabilistic Inference0
Idiom Paraphrases: Seventh Heaven vs Cloud NineCode0
Towards the Unsupervised Acquisition of Implicit Semantic Roles0
Noise or additional information? Leveraging crowdsource annotation item agreement for natural language tasks.0
An Exploration of Discourse-Based Sentence Spaces for Compositional Distributional Semantics0
Predicting Correlations Between Lexical Alignments and Semantic Inferences0
Large-Scale Acquisition of Entailment Pattern Pairs by Exploiting Transitivity0
Feature-Rich Two-Stage Logistic Regression for Monolingual Alignment0
Memory-Based Acquisition of Argument Structures and its Application to Implicit Role Detection0
Measuring Semantic Similarity for Bengali Tweets Using WordNet0
Ordering adverbs by their scaling effect on adjective intensity0
Visually-Verifiable Textual Entailment: A Challenge Task for Combining Language and Vision0
Zero Alignment of Verb Arguments in a Parallel Treebank0
Adding Semantics to Data-Driven Paraphrasing0
Annotating Entailment Relations for Shortanswer Questions0
Discourse-sensitive Automatic Identification of Generic Expressions0
Semantic Parsing for Textual Entailment0
Transition-based Dependency DAG Parsing Using Dynamic Oracles0
Exploiting Image Generality for Lexical Entailment Detection0
Perceptually Grounded Selectional Preferences0
A Unified Kernel Approach for Learning Typed Sentence Rewritings0
Concept Extensions as the Basis for Vector-Space Semantics: Combining Distributional and Ontological Information about Entities0
I do not disagree: leveraging monolingual alignment to detect disagreement in dialogue0
FrameNet+: Fast Paraphrastic Tripling of FrameNet0
Structural Representations for Learning Relations between Pairs of Texts0
PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification0
ECNU: Leveraging Word Embeddings to Boost Performance for Paraphrase in Twitter0
Recognizing Textual Entailment using Dependency Analysis and Machine Learning0
Ckylark: A More Robust PCFG-LA ParserCode0
TALN-UPF: Taxonomy Learning Exploiting CRF-Based Hypernym Extraction on Encyclopedic Definitions0
Show:102550
← PrevPage 34 of 40Next →

Benchmark Results

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