LetTokenBurnMicrosoft Research Paraphrase Corpus
Microsoft Research Paraphrase Corpus (MRPC) is a corpus consists of 5,801 sentence pairs collected from newswire articles.
$ npm i -g lettokenburn-cli$ ltb bench info mrpc
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| T5-11B | 90.0 | N/A | Independent | medium | Oct 23, 2019 | arxiv.org |
| ERNIE | 88.2 | N/A | Independent | medium | May 17, 2019 | arxiv.org |
| ERNIE 2.0 Large | 87.4 | N/A | Independent | medium | Jul 29, 2019 | arxiv.org |
| ERNIE 2.0 Base | 86.1 | N/A | Independent | medium | Jul 29, 2019 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Microsoft Research Paraphrase Corpus (MRPC) is a corpus consists of 5,801 sentence pairs collected from newswire articles. Each pair is labelled if it is a paraphrase or not by human annotators. The whole set is divided into a training subset (4,076 sentence pairs of which 2,753 are paraphrases) and a test subset (1,725 pairs of which 1,147 are paraphrases).
Source: Exploiting Semantic Annotations and Q-Learning for Constructing an Efficient Hierarchy/Graph Texts Organization Image Source: https://www.aclweb.org/anthology/I05-5002.pdf