言語タスクの評価指標: ROUGE, METEOR, EM

Pythonで学ぶ LLM 入門

Jasmin Ludolf

Senior Data Science Content Developer, DataCamp

LLM のタスクと指標

言語タスクの評価指標

LLM のタスクと指標

言語タスクの評価指標

LLM のタスクと指標

言語タスクの評価指標

ROUGE

ROUGE: 生成要約と参照要約の類似度
- n-gram と重複を評価
- predictions: LLM の出力
- references: 人手の要約

Comparing the cat sat on the mat and the cat is on the mat

ROUGE

rouge = evaluate.load("rouge")
predictions = ["""as we learn more about the frequency and size distribution of 
exoplanets, we are discovering that terrestrial planets are exceedingly common."""]
references = ["""The more we learn about the frequency and size distribution of 
exoplanets, the more confident we are that they are exceedingly common."""]

ROUGE スコア:

rouge1: ユニグラムの一致
rouge2: バイグラムの一致
rougeL: 長い共通部分列

ROUGE の出力

ROUGE スコア:

rouge1: ユニグラムの一致
rouge2: バイグラムの一致
rougeL: 長い共通部分列

スコアは0〜1: 高いほど類似度が高い

results = rouge.compute(predictions=predictions,
                         references=references)

print(results)

{'rouge1': 0.7441860465116279, 
'rouge2': 0.4878048780487805, 
'rougeL': 0.6976744186046512, 
'rougeLsum': 0.6976744186046512}

METEOR

METEOR: 語形変化、類義、語順など言語的特徴を考慮

bleu = evaluate.load("bleu")
meteor = evaluate.load("meteor")


prediction = ["He thought it right and necessary to become a knight-errant, roaming 
              the world in armor, seeking adventures and practicing the deeds he 
              had read about in chivalric tales."]

reference = ["He believed it was proper and essential to transform into a 
             knight-errant, traveling the world in armor, pursuing adventures, and 
             enacting the heroic deeds he had encountered in tales of chivalry."]

METEOR

results_bleu = bleu.compute(predictions=pred, references=ref)
results_meteor = meteor.compute(predictions=pred, references=ref)
print("Bleu: ", results_bleu['bleu'])
print("Meteor: ", results_meteor['meteor'])

Bleu:  0.19088841781992524
Meteor:  0.5350702240481536

0-1 のスコア: 高いほど良い

質問応答

言語タスクの評価指標

Exact Match (EM)

Exact Match (EM): LLM の出力が参照解答と完全一致なら 1

通常は F1 スコアと併用

from evaluate import load
em_metric = load("exact_match")

exact_match = evaluate.load("exact_match")
predictions = ["The cat sat on the mat.",
               "Theaters are great.", 
               "Like comparing oranges and apples."]
references = ["The cat sat on the mat?", 
              "Theaters are great.", 
              "Like comparing apples and oranges."]

results = exact_match.compute(
  references=references, predictions=predictions)
print(results)

{'exact_match': 0.3333333333333333}

Passons à la pratique !

Pythonで学ぶ LLM 入門