Discriminative Improvements to Distributional Sentence Similarity
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Semantic Textual Similarity | MRPC | TF-KLD | Accuracy | 80.4% | # 34 | |
F1 | 85.9% | # 14 | ||||
Paraphrase Identification | MSRP | FEAT2, TFKLD, SVM, Fine-grained features | Accuracy | 80.41 | # 1 | |
F1 | 85.96 | # 1 | ||||
Paraphrase Identification | MSRP | NMF factorization-unigrams-TFKLD | Accuracy | 72.75 | # 2 | |
F1 | 81.48 | # 2 | ||||
Semantic Textual Similarity | SentEval | TF-KLD | MRPC | 80.4/85.9 | # 1 | |
SICK-R | - | # 3 | ||||
SICK-E | - | # 3 | ||||
STS | - | # 1 |
Methods
No methods listed for this paper. Add
relevant methods here