SOTAVerified

Semantic Similarity

The main objective Semantic Similarity is to measure the distance between the semantic meanings of a pair of words, phrases, sentences, or documents. For example, the word “car” is more similar to “bus” than it is to “cat”. The two main approaches to measuring Semantic Similarity are knowledge-based approaches and corpus-based, distributional methods.

Source: Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 1564 papers

TitleStatusHype
CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model BiasCode1
Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic FactorsCode1
Hard negative examples are hard, but usefulCode1
Catch-A-Waveform: Learning to Generate Audio from a Single Short ExampleCode1
CgAT: Center-Guided Adversarial Training for Deep Hashing-Based RetrievalCode1
CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented GenerationCode1
Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMsCode1
Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation LearningCode1
Improving Language Understanding by Generative Pre-TrainingCode1
Class-relation Knowledge Distillation for Novel Class DiscoveryCode1
CmdCaliper: A Semantic-Aware Command-Line Embedding Model and Dataset for Security ResearchCode1
CODER: Knowledge infused cross-lingual medical term embedding for term normalizationCode1
Do Vision and Language Encoders Represent the World Similarly?Code1
RACE: Retrieval-Augmented Commit Message GenerationCode1
Fast and Accurate Deep Bidirectional Language Representations for Unsupervised LearningCode1
DiffSim: Taming Diffusion Models for Evaluating Visual SimilarityCode1
Describing Sets of Images with Textual-PCACode1
DIP: Dual Incongruity Perceiving Network for Sarcasm DetectionCode1
ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive SummarizationCode1
Deep Representational Re-tuning using Contrastive TensionCode1
A Semantic-based Method for Unsupervised Commonsense Question AnsweringCode1
A large-scale computational study of content preservation measures for text style transfer and paraphrase generationCode1
R&R: Metric-guided Adversarial Sentence GenerationCode1
Deep Metric Learning by Online Soft Mining and Class-Aware AttentionCode1
A Simple Long-Tailed Recognition Baseline via Vision-Language ModelCode1
Demystifying and Extracting Fault-indicating Information from Logs for Failure DiagnosisCode1
AstroCLIP: A Cross-Modal Foundation Model for GalaxiesCode1
DeepSim: Semantic similarity metrics for learned image registrationCode1
Attributable Visual Similarity LearningCode1
Automated radiology report generation using conditioned transformersCode1
Audio-Visual Class-Incremental LearningCode1
Distinguish Confusion in Legal Judgment Prediction via Revised Relation KnowledgeCode1
Discrete Optimization for Unsupervised Sentence Summarization with Word-Level ExtractionCode1
DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous DrivingCode1
A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity RewardsCode1
AutoGCL: Automated Graph Contrastive Learning via Learnable View GeneratorsCode1
3D-AVS: LiDAR-based 3D Auto-Vocabulary SegmentationCode1
DataSculpt: Crafting Data Landscapes for Long-Context LLMs through Multi-Objective PartitioningCode1
Automatic Generation of Topic LabelsCode1
ELITE: Embedding-Less retrieval with Iterative Text ExplorationCode1
C-STS: Conditional Semantic Textual SimilarityCode1
Balancing Lexical and Semantic Quality in Abstractive SummarizationCode1
DECAF: Deep Extreme Classification with Label FeaturesCode1
Evaluating Document Representations for Content-based Legal Literature RecommendationsCode1
Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCOCode1
CBLUE: A Chinese Biomedical Language Understanding Evaluation BenchmarkCode1
FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated LearningCode1
Few-Shot Class-Incremental Learning via Training-Free Prototype CalibrationCode1
FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual ModelsCode1
COPNER: Contrastive Learning with Prompt Guiding for Few-shot Named Entity RecognitionCode1
Show:102550
← PrevPage 2 of 32Next →
All datasetsAnnotated corpus for semantic similarity of clinical trial outcomes (expanded corpus)Annotated corpus for semantic similarity of clinical trial outcomes (original corpus)SICKBIOSSESCHIP-STSClinicalSTSMedSTS

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1BioBERT (pre-trained on PubMed abstracts + PMC, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus")F193.38—Unverified
2SciBERT uncased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus")F191.51—Unverified
3SciBERT cased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus")F190.69—Unverified
4BERT-Base uncased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus")F189.16—Unverified
5BERT-Base cased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus")F189.12—Unverified
#ModelMetricClaimedVerifiedStatus
1BioBERT (pre-trained on PubMed abstracts + PMC, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")F189.75—Unverified
2SciBERT cased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")F189.3—Unverified
3SciBERT uncased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")F189.3—Unverified
4BERT-Base uncased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")F186.8—Unverified
5BERT-Base cased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")F184.21—Unverified
#ModelMetricClaimedVerifiedStatus
1Doc2VecCMSE0.31—Unverified
2LSTM (Tai et al., 2015)MSE0.28—Unverified
3Bidirectional LSTM (Tai et al., 2015)MSE0.27—Unverified
4combine-skip (Kiros et al., 2015)MSE0.27—Unverified
5Dependency Tree-LSTM (Tai et al., 2015)MSE0.25—Unverified
#ModelMetricClaimedVerifiedStatus
1BioLinkBERT (large)Pearson Correlation0.94—Unverified
2BioLinkBERT (base)Pearson Correlation0.93—Unverified
3NCBI_BERT(base) (P+M)Pearson Correlation0.92—Unverified
#ModelMetricClaimedVerifiedStatus
1MacBERT-largeMacro F185.6—Unverified
#ModelMetricClaimedVerifiedStatus
1CharacterBERT (base, medical, ensemble)Pearson Correlation85.62—Unverified
#ModelMetricClaimedVerifiedStatus
1NCBI_BERT(base) (P+M)Pearson Correlation0.85—Unverified