Paragraph Vector

Reported on 2 benchmarks across 2 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing1 result

  • Sentence EmbeddingsonBIOSSES
    Pearson Correlation· uses extra data
    0.787
    best: 0.871 (Supervised combination of: Jaccard, Q-gram, sent2vec, Paragraph vector DM, skip-thoughts, fastText)

Methodology1 result

  • Representation LearningonBIOSSES
    Pearson Correlation· uses extra data
    0.787
    best: 0.871 (Supervised combination of: Jaccard, Q-gram, sent2vec, Paragraph vector DM, skip-thoughts, fastText)