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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 201–225 of 1564 papers

Title	Date	Tasks	Status	Hype	Score
Evaluating Document Representations for Content-based Legal Literature Recommendations	Apr 28, 2021	Recommendation SystemsRepresentation Learning	CodeCode Available	1	5
Balancing Lexical and Semantic Quality in Abstractive Summarization	May 17, 2023	Abstractive Text SummarizationRe-Ranking	CodeCode Available	1	5
Semantic Pyramid for Image Generation	Mar 13, 2020	General ClassificationImage Generation	CodeCode Available	1	5
Explainable Legal Case Matching via Inverse Optimal Transport-based Rationale Extraction	Jul 9, 2022	Explanation GenerationFairness	CodeCode Available	1	5
Neural CRF Model for Sentence Alignment in Text Simplification	May 5, 2020	ArticlesSemantic Similarity	CodeCode Available	1	5
Semantic similarity metrics for learned image registration	Apr 20, 2021	Image RegistrationSemantic Similarity	CodeCode Available	1	5
Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning	Apr 17, 2020	CPULanguage Modeling	CodeCode Available	1	5
Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration	Dec 8, 2023	class-incremental learningClass Incremental Learning	CodeCode Available	1	5
Sentence Embedding Models for Ancient Greek Using Multilingual Knowledge Distillation	Aug 24, 2023	Authorship AttributionKnowledge Distillation	CodeCode Available	1	5
Familiarity: Better Evaluation of Zero-Shot Named Entity Recognition by Quantifying Label Shifts in Synthetic Training Data	Dec 13, 2024	named-entity-recognitionNamed Entity Recognition	CodeCode Available	1	5
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders	Apr 16, 2021	Contrastive LearningCross-Lingual Semantic Textual Similarity	CodeCode Available	1	5
FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning	Dec 14, 2023	Computational EfficiencyFederated Learning	CodeCode Available	1	5
Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning	Nov 29, 2021	Contrastive LearningLinear evaluation	CodeCode Available	1	5
Efficient Neural Ranking using Forward Indexes	Oct 12, 2021	CPUDocument Ranking	CodeCode Available	1	5
Few-Shot Object Detection via Association and DIscrimination	Nov 23, 2021	Few-Shot Object DetectionObject	CodeCode Available	1	5
Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling	May 10, 2022	Few-Shot Image ClassificationGeneral Classification	CodeCode Available	1	5
FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models	May 23, 2023	Language ModelingLanguage Modelling	CodeCode Available	1	5
SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples	Jan 16, 2022	Contrastive LearningData Augmentation	CodeCode Available	1	5
SPICE: Semantic Pseudo-labeling for Image Clustering	Mar 17, 2021	ClusteringContrastive Learning	CodeCode Available	1	5
Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models	Dec 15, 2023	BenchmarkingCode Summarization	CodeCode Available	1	5
Retrieve and Refine: Exemplar-based Neural Comment Generation	Oct 9, 2020	Code Comment GenerationComment Generation	CodeCode Available	1	5
Generalized Product Quantization Network for Semi-supervised Image Retrieval	Feb 26, 2020	Image RetrievalMetric Learning	CodeCode Available	1	5
HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization	Jan 1, 2022	DiversitySemantic Segmentation	CodeCode Available	0	5
Hybrid Semantic Recommender System for Chemical Compounds	Jan 21, 2020	Collaborative FilteringRecommendation Systems	CodeCode Available	0	5
How does BERT capture semantics? A closer look at polysemous words	Nov 1, 2020	Semanticity predictionSemantic Similarity	CodeCode Available	0	5

Show:10 25 50

← PrevPage 9 of 63Next →

All datasets Annotated corpus for semantic similarity of clinical trial outcomes (expanded corpus)Annotated corpus for semantic similarity of clinical trial outcomes (original corpus)SICK BIOSSES CHIP-STS ClinicalSTS MedSTS

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	BioBERT (pre-trained on PubMed abstracts + PMC, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus")	F1	93.38	—	Unverified
2	SciBERT uncased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus")	F1	91.51	—	Unverified
3	SciBERT cased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus")	F1	90.69	—	Unverified
4	BERT-Base uncased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus")	F1	89.16	—	Unverified
5	BERT-Base cased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, expanded corpus")	F1	89.12	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BioBERT (pre-trained on PubMed abstracts + PMC, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")	F1	89.75	—	Unverified
2	SciBERT cased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")	F1	89.3	—	Unverified
3	SciBERT uncased (SciVocab, fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")	F1	89.3	—	Unverified
4	BERT-Base uncased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")	F1	86.8	—	Unverified
5	BERT-Base cased (fine-tuned on "Annotated corpus for semantic similarity of clinical trial outcomes, original corpus")	F1	84.21	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Doc2VecC	MSE	0.31	—	Unverified
2	LSTM (Tai et al., 2015)	MSE	0.28	—	Unverified
3	Bidirectional LSTM (Tai et al., 2015)	MSE	0.27	—	Unverified
4	combine-skip (Kiros et al., 2015)	MSE	0.27	—	Unverified
5	Dependency Tree-LSTM (Tai et al., 2015)	MSE	0.25	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BioLinkBERT (large)	Pearson Correlation	0.94	—	Unverified
2	BioLinkBERT (base)	Pearson Correlation	0.93	—	Unverified
3	NCBI_BERT(base) (P+M)	Pearson Correlation	0.92	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MacBERT-large	Macro F1	85.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CharacterBERT (base, medical, ensemble)	Pearson Correlation	85.62	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	NCBI_BERT(base) (P+M)	Pearson Correlation	0.85	—	Unverified