Extractive Text Summarization
Given a document, selecting a subset of the words or sentences which best represents a summary of the document.
Papers
No papers found.
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | HAHSum | ROUGE-1 | 44.68 | — | Unverified |
| 2 | Scaled-MatchSum | ROUGE-1 | 44.51 | — | Unverified |
| 3 | MatchSum | ROUGE-1 | 44.41 | — | Unverified |
| 4 | A2Summ | ROUGE-1 | 44.11 | — | Unverified |
| 5 | NeRoBERTa | ROUGE-1 | 43.86 | — | Unverified |
| 6 | BERT-ext + RL | ROUGE-1 | 42.76 | — | Unverified |
| 7 | PNBERT | ROUGE-1 | 42.69 | — | Unverified |
| 8 | HIBERT | ROUGE-1 | 42.37 | — | Unverified |
| 9 | HER | ROUGE-1 | 42.3 | — | Unverified |
| 10 | NeuSUM | ROUGE-1 | 41.59 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Longformer-Base | ROUGE-L | 57.21 | — | Unverified |
| 2 | GPT2-Medium | ROUGE-L | 53.23 | — | Unverified |
| 3 | BERT-Large | ROUGE-L | 49.98 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MemSum (extractive) | Avg. Test Rouge1 | 59.43 | — | Unverified |
| 2 | HEPOS | Avg. Test Rouge1 | 56.86 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Pre-training-meets-Clustering-A-Hybrid-Extractive-Multi-Document-Summarization-Model | Test ROGUE-1 | 34.01 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Abs | ROUGE-1 | 26.55 | — | Unverified |