Skip to content

GitLab

"megatron/fused_kernels/__init__.py" did not exist on "6c3f6c7bb582b4509b28b64c3772e56f11627b7f"
Switch branch/tag
Find file Normal viewHistoryPermalink
utils.py 3.39 KB
Newer Older
PabloAgustin's avatar
New healthcare benchmark: careqa (#2714)  
PabloAgustin committed
1
2
3
4
5
6
7
8
9
10
11
12
13 
import numpy as np


try:
    import evaluate

    bleu = evaluate.load("bleu")
    rouge = evaluate.load("rouge")
    bertscore = evaluate.load("bertscore")
    bleurt = evaluate.load("bleurt", "bleurt-base-512", module_type="metric")

except (ModuleNotFoundError, ImportError):
    raise ModuleNotFoundError(
Idan Tene's avatar
Fix medical benchmarks import (#3151)  
Idan Tene committed
14
15
16 
        "Please install evaluation metrics via pip install evaluate bert-score "
        "rouge_score>=0.1.2 nltk absl-py "
        "git+https://github.com/google-research/bleurt.git"
PabloAgustin's avatar
New healthcare benchmark: careqa (#2714)  
PabloAgustin committed
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130 
    )
except Exception as e:
    raise RuntimeError(
        f"Error loading evaluation metrics: {str(e)}. Please check your installation."
    )


def doc_eval(pred, refs):
    try:
        bleu_results = bleu.compute(predictions=pred, references=refs)
    except Exception as e:
        print(f"Bleu error: {e}")
        bleu_results = {"bleu": np.nan}

    try:
        rouge_results = rouge.compute(predictions=pred, references=refs)
    except Exception as e:
        print(f"Rouge error: {e}")
        rouge_results = {"rouge1": np.nan, "rouge2": np.nan, "rougeL": np.nan}

    try:
        bleurt_scores = bleurt.compute(predictions=pred, references=refs)["scores"]
    except Exception as e:
        print(f"Bleurt error: {e}")
        bleurt_scores = [np.nan]

    try:
        bert_scores = bertscore.compute(predictions=pred, references=refs, lang="en")[
            "f1"
        ]
    except Exception as e:
        print(f"Bert error: {e}")
        bert_scores = [np.nan]

    if bleu_results["bleu"] == 0:
        # Sometimes bleu is 0.0 and this breaks the stderr computation.
        bleu_results["bleu"] += 1e-5

    results = {
        "bleu": bleu_results["bleu"],
        "rouge1": rouge_results["rouge1"],
        "rouge2": rouge_results["rouge2"],
        "rougeL": rouge_results["rougeL"],
        "bleurt": np.mean(bleurt_scores),
        "bert_score": np.mean(bert_scores),
    }

    return results


def doc_to_text_raw(doc) -> str:
    return doc["description"]


def doc_to_target_raw(doc) -> str:
    return doc["utterances"]["utterance"][1]


def process_results_gen_raw(doc, results):
    pred, refs = [results[0]], [doc_to_target_raw(doc)]

    if len(refs[0]) < 1 or len(pred[0]) < 1:
        return {
            "bleu": np.nan,
            "rouge1": np.nan,
            "rouge2": np.nan,
            "rougeL": np.nan,
            "bleurt": np.nan,
            "bert_score": np.nan,
        }

    results = doc_eval(pred, refs)

    return {
        "bleu": results["bleu"],
        "rouge1": results["rouge1"],
        "rouge2": results["rouge2"],
        "rougeL": results["rougeL"],
        "bleurt": results["bleurt"],
        "bert_score": results["bert_score"],
    }


def doc_to_text_qsumm(doc) -> str:
    return doc["src"]


def doc_to_target_qsumm(doc) -> str:
    return doc["tgt"]


def process_results_gen_qsumm(doc, results):
    pred, refs = [results[0]], [doc_to_target_qsumm(doc)]

    if len(refs[0]) < 1 or len(pred[0]) < 1:
        return {
            "bleu": np.nan,
            "rouge1": np.nan,
            "rouge2": np.nan,
            "rougeL": np.nan,
            "bleurt": np.nan,
            "bert_score": np.nan,
        }

    results = doc_eval(pred, refs)

    return {
        "bleu": results["bleu"],
        "rouge1": results["rouge1"],
        "rouge2": results["rouge2"],
        "rougeL": results["rougeL"],
        "bleurt": results["bleurt"],
        "bert_score": results["bert_score"],
    }