T5 Base Squad Qg Ae

🚀 lmqg/t5-base-squad-qg-ae 模型卡片

本模型是 t5-base 的微調版本，通過 lmqg 在 lmqg/qg_squad（數據集名稱：default）上聯合進行問題生成和答案提取任務的微調。

🚀 快速開始

模型概述

模型使用

使用 lmqg 庫

from lmqg import TransformersQG

# 初始化模型
model = TransformersQG(language="en", model="lmqg/t5-base-squad-qg-ae")

# 模型預測
question_answer_pairs = model.generate_qa("William Turner was an English painter who specialised in watercolour landscapes")

使用 transformers 庫

from transformers import pipeline

pipe = pipeline("text2text-generation", "lmqg/t5-base-squad-qg-ae")

# 答案提取
answer = pipe("generate question: <hl> Beyonce <hl> further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records.")

# 問題生成
question = pipe("extract answers: <hl> Beyonce further expanded her acting career, starring as blues singer Etta James in the 2008 musical biopic, Cadillac Records. <hl> Her performance in the film received praise from critics, and she garnered several nominations for her portrayal of James, including a Satellite Award nomination for Best Supporting Actress, and a NAACP Image Award nomination for Outstanding Supporting Actress.")

📚 詳細文檔

評估指標

問題生成指標

原始指標文件

問題與答案生成指標

原始指標文件

答案提取指標

原始指標文件

訓練超參數

微調期間使用的超參數如下：

• 數據集路徑：lmqg/qg_squad
• 數據集名稱：default
• 輸入類型：['paragraph_answer', 'paragraph_sentence']
• 輸出類型：['question', 'answer']
• 前綴類型：['qg', 'ae']
• 模型：t5-base
• 最大長度：512
• 最大輸出長度：32
• 訓練輪數：6
• 批次大小：32
• 學習率：0.0001
• 混合精度訓練：False
• 隨機種子：1
• 梯度累積步數：4
• 標籤平滑：0.15

完整配置可在 微調配置文件 中找到。

📄 許可證

本模型使用 CC BY 4.0 許可證。

📖 引用

@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",
}