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
Showing 1451–1475 of 1564 papers
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
| # | 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 |