senteval_output/senteval.json

{
    "STSBenchmark": {
        "train": {
            "pearson": [
                0.759143306453737,
                0.0
            ],
            "spearman": [
                0.732317209733238,
                0.0
            ],
            "nsamples": 5749
        },
        "dev": {
            "pearson": [
                0.7746081783379711,
                2.2556430824992415e-300
            ],
            "spearman": [
                0.7800424504336374,
                2.5466091811087085e-307
            ],
            "nsamples": 1500
        },
        "test": {
            "pearson": [
                0.7580850707783013,
                6.51859239939566e-258
            ],
            "spearman": [
                0.7560754511600052,
                8.850873074119353e-256
            ],
            "nsamples": 1379
        },
        "all": {
            "pearson": {
                "all": 0.7620304519086235,
                "mean": 0.7639455185233365,
                "wmean": 0.7616627780381048
            },
            "spearman": {
                "all": 0.7488342650348635,
                "mean": 0.7561450371089601,
                "wmean": 0.7444116088962087
            }
        }
    },
    "SICKRelatedness": {
        "train": {
            "pearson": [
                0.7660762263543586,
                0.0
            ],
            "spearman": [
                0.6943387839868075,
                0.0
            ],
            "nsamples": 4500
        },
        "dev": {
            "pearson": [
                0.7787463535407387,
                6.565381473913046e-103
            ],
            "spearman": [
                0.724076491124677,
                2.2464753888818782e-82
            ],
            "nsamples": 500
        },
        "test": {
            "pearson": [
                0.7585953923013815,
                0.0
            ],
            "spearman": [
                0.6847050750070173,
                0.0
            ],
            "nsamples": 4927
        },
        "all": {
            "pearson": {
                "all": 0.7629449380408607,
                "mean": 0.7678059907321595,
                "wmean": 0.7630014801283258
            },
            "spearman": {
                "all": 0.6909722716792152,
                "mean": 0.7010401167061673,
                "wmean": 0.6910551705512789
            }
        }
    },
    "MR": {
        "devacc": 81.13,
        "acc": 80.72,
        "ndev": 10662,
        "ntest": 10662
    },
    "CR": {
        "devacc": 87.1,
        "acc": 85.35,
        "ndev": 3775,
        "ntest": 3775
    },
    "SUBJ": {
        "devacc": 95.37,
        "acc": 94.83,
        "ndev": 10000,
        "ntest": 10000
    },
    "MPQA": {
        "devacc": 88.87,
        "acc": 88.84,
        "ndev": 10606,
        "ntest": 10606
    },
    "SST2": {
        "devacc": 83.72,
        "acc": 84.84,
        "ndev": 872,
        "ntest": 1821
    },
    "TREC": {
        "devacc": 79.31,
        "acc": 85.4,
        "ndev": 5452,
        "ntest": 500
    },
    "MRPC": {
        "devacc": 71.32,
        "acc": 68.93,
        "f1": 78.8,
        "ndev": 4076,
        "ntest": 1725
    },
    "STS12": {
        "MSRpar": {
            "pearson": [
                0.4802609709856894,
                1.5548549952823705e-44
            ],
            "spearman": [
                0.4768543559246008,
                7.614791350529852e-44
            ],
            "nsamples": 750
        },
        "MSRvid": {
            "pearson": [
                0.8263319209416204,
                1.080221265522035e-188
            ],
            "spearman": [
                0.8252791857619619,
                8.356577398931468e-188
            ],
            "nsamples": 750
        },
        "SMTeuroparl": {
            "pearson": [
                0.5184489923467462,
                6.1406360676578446e-33
            ],
            "spearman": [
                0.6230131131079721,
                1.0590062591812851e-50
            ],
            "nsamples": 459
        },
        "surprise.OnWN": {
            "pearson": [
                0.7315874470125636,
                1.414322871092147e-126
            ],
            "spearman": [
                0.6731301571473148,
                4.0960228359103546e-100
            ],
            "nsamples": 750
        },
        "surprise.SMTnews": {
            "pearson": [
                0.6259156885670977,
                8.739441951714742e-45
            ],
            "spearman": [
                0.6148988213247114,
                7.33074623929432e-43
            ],
            "nsamples": 399
        },
        "all": {
            "pearson": {
                "all": 0.623383289827507,
                "mean": 0.6365090039707434,
                "wmean": 0.6487592346944445
            },
            "spearman": {
                "all": 0.606079829047924,
                "mean": 0.6426351266533122,
                "wmean": 0.6476047048746869
            }
        }
    },
    "STS13": {
        "FNWN": {
            "pearson": [
                0.5661863937046698,
                2.0580012282455086e-17
            ],
            "spearman": [
                0.5912700246061035,
                3.3253838782016723e-19
            ],
            "nsamples": 189
        },
        "headlines": {
            "pearson": [
                0.7825601400543155,
                4.2299360961974125e-156
            ],
            "spearman": [
                0.7841745697183816,
                3.6476628073513e-157
            ],
            "nsamples": 750
        },
        "OnWN": {
            "pearson": [
                0.794529783804957,
                3.311330886766186e-123
            ],
            "spearman": [
                0.7834024923042585,
                1.4890472209808275e-117
            ],
            "nsamples": 561
        },
        "all": {
            "pearson": {
                "all": 0.7471361547131256,
                "mean": 0.7144254391879808,
                "wmean": 0.7597736947770001
            },
            "spearman": {
                "all": 0.7564536182897523,
                "mean": 0.7196156955429145,
                "wmean": 0.7595798400813525
            }
        }
    },
    "STS14": {
        "deft-forum": {
            "pearson": [
                0.5270887834584671,
                1.541470939768766e-33
            ],
            "spearman": [
                0.5112851401228272,
                2.4363986591055635e-31
            ],
            "nsamples": 450
        },
        "deft-news": {
            "pearson": [
                0.7735386895034391,
                5.576824423082716e-61
            ],
            "spearman": [
                0.721172124183031,
                1.986170265393856e-49
            ],
            "nsamples": 300
        },
        "headlines": {
            "pearson": [
                0.7545133819317689,
                5.912159102599232e-139
            ],
            "spearman": [
                0.7126401838119187,
                2.8437071308486684e-117
            ],
            "nsamples": 750
        },
        "images": {
            "pearson": [
                0.8323456329452497,
                6.921690784176308e-194
            ],
            "spearman": [
                0.7937433816131229,
                1.1474485172111374e-163
            ],
            "nsamples": 750
        },
        "OnWN": {
            "pearson": [
                0.8297923551143387,
                1.175057263022769e-191
            ],
            "spearman": [
                0.826236205234858,
                1.3018028294306147e-188
            ],
            "nsamples": 750
        },
        "tweet-news": {
            "pearson": [
                0.7558799639584549,
                9.788201645414497e-140
            ],
            "spearman": [
                0.6845652322701915,
                8.460582099195036e-105
            ],
            "nsamples": 750
        },
        "all": {
            "pearson": {
                "all": 0.7159862351857734,
                "mean": 0.7455264678186196,
                "wmean": 0.7596400159652537
            },
            "spearman": {
                "all": 0.6704800621775756,
                "mean": 0.7082737112059916,
                "wmean": 0.7224849873354
            }
        }
    },
    "STS15": {
        "answers-forums": {
            "pearson": [
                0.7317275686935678,
                4.532297271121567e-64
            ],
            "spearman": [
                0.7407727747177331,
                1.972401483293033e-66
            ],
            "nsamples": 375
        },
        "answers-students": {
            "pearson": [
                0.7050737483230498,
                9.136794973091405e-114
            ],
            "spearman": [
                0.7064217578173171,
                2.2091874983666628e-114
            ],
            "nsamples": 750
        },
        "belief": {
            "pearson": [
                0.783394736380794,
                4.7974747142716894e-79
            ],
            "spearman": [
                0.7998064345059992,
                1.0770053295383067e-84
            ],
            "nsamples": 375
        },
        "headlines": {
            "pearson": [
                0.813583787598092,
                2.5592603175894345e-178
            ],
            "spearman": [
                0.8095733522782433,
                3.220682833365799e-175
            ],
            "nsamples": 750
        },
        "images": {
            "pearson": [
                0.8641888241232765,
                2.5653257492197874e-225
            ],
            "spearman": [
                0.869236692916196,
                4.9395933314044357e-231
            ],
            "nsamples": 750
        },
        "all": {
            "pearson": {
                "all": 0.7901758719755425,
                "mean": 0.779593733023756,
                "wmean": 0.7851018781453998
            },
            "spearman": {
                "all": 0.7993930145058169,
                "mean": 0.7851622024470977,
                "wmean": 0.7888803519059057
            }
        }
    },
    "STS16": {
        "answer-answer": {
            "pearson": [
                0.732325384111771,
                6.031948033432114e-44
            ],
            "spearman": [
                0.7331760524557248,
                4.2918539327373104e-44
            ],
            "nsamples": 254
        },
        "headlines": {
            "pearson": [
                0.7751129917838497,
                3.6445698860447696e-51
            ],
            "spearman": [
                0.7759120405190852,
                2.4798809912199763e-51
            ],
            "nsamples": 249
        },
        "plagiarism": {
            "pearson": [
                0.8073018229023751,
                3.908432651513822e-54
            ],
            "spearman": [
                0.8201128848961844,
                3.380055386535779e-57
            ],
            "nsamples": 230
        },
        "postediting": {
            "pearson": [
                0.8262293698872258,
                2.999128754083028e-62
            ],
            "spearman": [
                0.8467835716176686,
                2.7503849185111653e-68
            ],
            "nsamples": 244
        },
        "question-question": {
            "pearson": [
                0.7751346076550414,
                3.733475629577834e-43
            ],
            "spearman": [
                0.7850104595896853,
                6.270227463768292e-45
            ],
            "nsamples": 209
        },
        "all": {
            "pearson": {
                "all": 0.7817024776005017,
                "mean": 0.7832208352680526,
                "wmean": 0.7827118895771512
            },
            "spearman": {
                "all": 0.7931904794778135,
                "mean": 0.7921990018156697,
                "wmean": 0.7915153089950118
            }
        }
    },
    "eval_senteval-STS12": 0.606079829047924,
    "eval_senteval-STS13": 0.7564536182897523,
    "eval_senteval-STS14": 0.6704800621775756,
    "eval_senteval-STS15": 0.7993930145058169,
    "eval_senteval-STS16": 0.7931904794778135,
    "eval_senteval-STSBenchmark": 0.7488342650348635,
    "eval_senteval-SICKRelatedness": 0.6909722716792152,
    "eval_senteval-avg_sts_7": 0.7236290771732802,
    "eval_senteval-MR": 81.13,
    "eval_senteval-CR": 87.1,
    "eval_senteval-SUBJ": 95.37,
    "eval_senteval-MPQA": 88.87,
    "eval_senteval-SST2": 83.72,
    "eval_senteval-TREC": 79.31,
    "eval_senteval-MRPC": 71.32,
    "eval_senteval-avg_transfer": 83.83142857142856
}