SOTAVerified

Semantic Textual Similarity

Semantic textual similarity deals with determining how similar two pieces of texts are. This can take the form of assigning a score from 1 to 5. Related tasks are paraphrase or duplicate identification.

Image source: Learning Semantic Textual Similarity from Conversations

Papers

Showing 201250 of 2381 papers

TitleStatusHype
Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text ModelsCode1
Instance Similarity Learning for Unsupervised Feature RepresentationCode1
Bootstrapped Unsupervised Sentence Representation LearningCode1
Multimodal Representation for Neural Code SearchCode1
Charformer: Fast Character Transformers via Gradient-based Subword TokenizationCode1
Catch-A-Waveform: Learning to Generate Audio from a Single Short ExampleCode1
Entity Concept-enhanced Few-shot Relation ExtractionCode1
Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical InferenceCode1
A Semantic-based Method for Unsupervised Commonsense Question AnsweringCode1
ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation TransferCode1
Cross-lingual Text Classification with Heterogeneous Graph Neural NetworkCode1
KLUE: Korean Language Understanding EvaluationCode1
Long Text Generation by Modeling Sentence-Level and Discourse-Level CoherenceCode1
Predicting Gene-Disease Associations with Knowledge Graph Embeddings over Multiple OntologiesCode1
FNet: Mixing Tokens with Fourier TransformsCode1
Paraphrastic Representations at ScaleCode1
Entailment as Few-Shot LearnerCode1
Semantic similarity metrics for learned image registrationCode1
R&R: Metric-guided Adversarial Sentence GenerationCode1
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersCode1
Generating Datasets with Pretrained Language ModelsCode1
How to Train BERT with an Academic BudgetCode1
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding LearningCode1
SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point CloudsCode1
Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language ModelsCode1
Automated radiology report generation using conditioned transformersCode1
PatentSBERTa: A Deep NLP based Hybrid Model for Patent Distance and Classification using Augmented SBERTCode1
On Semantic Similarity in Video RetrievalCode1
SPICE: Semantic Pseudo-labeling for Image ClusteringCode1
Real-time Relevant Recommendation SuggestionCode1
Scalable Learning With a Structural Recurrent Neural Network for Short-Term Traffic PredictionCode1
Distributional Formal SemanticsCode1
Unsupervised Extractive Summarization using Pointwise Mutual InformationCode1
Nyströmformer: A Nyström-Based Algorithm for Approximating Self-AttentionCode1
Deep Representational Re-tuning using Contrastive TensionCode1
Generating Natural Language Attacks in a Hard Label Black Box SettingCode1
Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-TuningCode1
RealFormer: Transformer Likes Residual AttentionCode1
MASKER: Masked Keyword Regularization for Reliable Text ClassificationCode1
Extended Few-Shot Learning: Exploiting Existing Resources for Novel TasksCode1
SemMT: A Semantic-based Testing Approach for Machine Translation SystemsCode1
DeepSim: Semantic similarity metrics for learned image registrationCode1
CODER: Knowledge infused cross-lingual medical term embedding for term normalizationCode1
On the Sentence Embeddings from Pre-trained Language ModelsCode1
A Statistical Framework for Low-bitwidth Training of Deep Neural NetworksCode1
Unsupervised Image-to-Image Translation via Pre-trained StyleGAN2 NetworkCode1
ComStreamClust: a communicative multi-agent approach to text clustering in streaming dataCode1
Retrieve and Refine: Exemplar-based Neural Comment GenerationCode1
An Unsupervised Sentence Embedding Method by Mutual Information MaximizationCode1
Weak-shot Fine-grained Classification via Similarity TransferCode1
Show:102550
← PrevPage 5 of 48Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SMARTRoBERTaDev Pearson Correlation92.8Unverified
2DeBERTa (large)Accuracy92.5Unverified
3SMART-BERTDev Pearson Correlation90Unverified
4MT-DNN-SMARTPearson Correlation0.93Unverified
5StructBERTRoBERTa ensemblePearson Correlation0.93Unverified
6Mnet-SimPearson Correlation0.93Unverified
7XLNet (single model)Pearson Correlation0.93Unverified
8T5-11BPearson Correlation0.93Unverified
9ALBERTPearson Correlation0.93Unverified
10RoBERTaPearson Correlation0.92Unverified
#ModelMetricClaimedVerifiedStatus
1AnglE-UAESpearman Correlation84.54Unverified
2ST5-XXLSpearman Correlation82.63Unverified
3ST5-LargeSpearman Correlation81.83Unverified
4ST5-XLSpearman Correlation81.66Unverified
5ST5-BaseSpearman Correlation81.14Unverified
6MPNet-multilingualSpearman Correlation80.73Unverified
7SGPT-5.8B-nliSpearman Correlation80.53Unverified
8MPNetSpearman Correlation80.28Unverified
9MiniLM-L12Spearman Correlation79.8Unverified
10SimCSE-BERT-supSpearman Correlation79.12Unverified
#ModelMetricClaimedVerifiedStatus
1MT-DNN-SMARTAccuracy93.7Unverified
2ALBERTAccuracy93.4Unverified
3RoBERTa (ensemble)Accuracy92.3Unverified
4BigBirdF191.5Unverified
5StructBERTRoBERTa ensembleAccuracy91.5Unverified
6FLOATER-largeAccuracy91.4Unverified
7SMARTAccuracy91.3Unverified
8RoBERTa-large 355M (MLP quantized vector-wise, fine-tuned)Accuracy91Unverified
9RoBERTa-large 355M + Entailment as Few-shot LearnerF191Unverified
10SpanBERTAccuracy90.9Unverified
#ModelMetricClaimedVerifiedStatus
1PromCSE-RoBERTa-large (0.355B)Spearman Correlation0.82Unverified
2PromptEOL+CSE+LLaMA-30BSpearman Correlation0.82Unverified
3PromptEOL+CSE+OPT-13BSpearman Correlation0.82Unverified
4SimCSE-RoBERTalargeSpearman Correlation0.82Unverified
5PromptEOL+CSE+OPT-2.7BSpearman Correlation0.81Unverified
6SentenceBERTSpearman Correlation0.75Unverified
7SRoBERTa-NLI-baseSpearman Correlation0.74Unverified
8SRoBERTa-NLI-largeSpearman Correlation0.74Unverified
9Dino (STS/̄🦕)Spearman Correlation0.74Unverified
10SBERT-NLI-largeSpearman Correlation0.74Unverified
#ModelMetricClaimedVerifiedStatus
1AnglE-LLaMA-7BSpearman Correlation0.91Unverified
2AnglE-LLaMA-7B-v2Spearman Correlation0.91Unverified
3PromptEOL+CSE+LLaMA-30BSpearman Correlation0.9Unverified
4PromptEOL+CSE+OPT-13BSpearman Correlation0.9Unverified
5PromptEOL+CSE+OPT-2.7BSpearman Correlation0.9Unverified
6PromCSE-RoBERTa-large (0.355B)Spearman Correlation0.89Unverified
7Trans-Encoder-BERT-large-bi (unsup.)Spearman Correlation0.89Unverified
8Trans-Encoder-BERT-large-cross (unsup.)Spearman Correlation0.88Unverified
9Trans-Encoder-RoBERTa-large-cross (unsup.)Spearman Correlation0.88Unverified
10SimCSE-RoBERTa-largeSpearman Correlation0.87Unverified