模型:
lmqg/mt5-small-itquad-qag
该模型是 google/mt5-small 的微调版本,用于在 lmqg 上的问题和答案对生成任务(数据集名称:default)。
from lmqg import TransformersQG
# initialize model
model = TransformersQG(language="it", model="lmqg/mt5-small-itquad-qag")
# model prediction
question_answer_pairs = model.generate_qa("Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.")
from transformers import pipeline
pipe = pipeline("text2text-generation", "lmqg/mt5-small-itquad-qag")
output = pipe("Dopo il 1971 , l' OPEC ha tardato ad adeguare i prezzi per riflettere tale deprezzamento.")
| Score | Type | Dataset | |
|---|---|---|---|
| QAAlignedF1Score (BERTScore) | 79.41 | default | 12313321 |
| QAAlignedF1Score (MoverScore) | 54.15 | default | 12313321 |
| QAAlignedPrecision (BERTScore) | 81.16 | default | 12313321 |
| QAAlignedPrecision (MoverScore) | 55.49 | default | 12313321 |
| QAAlignedRecall (BERTScore) | 77.79 | default | 12313321 |
| QAAlignedRecall (MoverScore) | 52.94 | default | 12313321 |
在微调过程中使用了以下超参数:
完整的配置信息可在 fine-tuning config file 中找到。
@inproceedings{ushio-etal-2022-generative,
title = "{G}enerative {L}anguage {M}odels for {P}aragraph-{L}evel {Q}uestion {G}eneration",
author = "Ushio, Asahi and
Alva-Manchego, Fernando and
Camacho-Collados, Jose",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, U.A.E.",
publisher = "Association for Computational Linguistics",
}