Bart Large Citesum Title

🚀 Bart-Large CiteSum (Titles)

這是在CiteSum上進行微調的facebook/bart-large模型。“src”列是輸入，“title”列是目標摘要。

✨ 主要特性

• 基於facebook/bart-large模型在CiteSum數據集上微調，用於文本摘要任務。
• 可根據輸入文本生成高質量的標題摘要。

📦 安裝指南

文檔未提及安裝步驟，暫不展示。

💻 使用示例

基礎用法

from transformers import pipeline
summarizer = pipeline("summarization", model="yuningm/bart-large-citesum-title")

article = ''' We describe a convolutional neural network that learns\
 feature representations for short textual posts using hashtags as a\
  supervised signal. The proposed approach is trained on up to 5.5 \
  billion words predicting 100,000 possible hashtags. As well as strong\
   performance on the hashtag prediction task itself, we show that its \
   learned representation of text (ignoring the hashtag labels) is useful\
    for other tasks as well. To that end, we present results on a document\
     recommendation task, where it also outperforms a number of baselines.
'''
summarizer(article)
# [{'summary_text': 'Learning Text Representations from Hashtags using Convolutional Neural Networks'}]

📚 詳細文檔

作者信息

作者

Yuning Mao, Ming Zhong, Jiawei Han

所屬機構

University of Illinois Urbana-Champaign
{yuningm2, mingz5, hanj}@illinois.edu

實驗結果

{
    "epoch": 6.78,
    "eval_gen_len": 17.1775,
    "eval_loss": 1.9626615047454834,
    "eval_rouge1": 51.4834,
    "eval_rouge2": 29.9178,
    "eval_rougeL": 45.4882,
    "eval_rougeLsum": 45.517,
    "eval_runtime": 351.9638,
    "eval_samples": 4681,
    "eval_samples_per_second": 13.3,
    "eval_steps_per_second": 0.21,
    "predict_gen_len": 17.1032,
    "predict_loss": 1.9391602277755737,
    "predict_rouge1": 52.0304,
    "predict_rouge2": 30.1511,
    "predict_rougeL": 45.9902,
    "predict_rougeLsum": 46.0068,
    "predict_runtime": 363.9691,
    "predict_samples": 4882,
    "predict_samples_per_second": 13.413,
    "predict_steps_per_second": 0.212,
    "train_loss": 1.0821667497907366,
    "train_runtime": 24401.3762,
    "train_samples": 82653,
    "train_samples_per_second": 65.57,
    "train_steps_per_second": 8.196
}

數據集描述

CiteSum：引用文本引導的科學極端摘要和低資源領域適應。
CiteSum包含來自科學論文引用文本的TLDR摘要，無需人工標註，使其規模比之前人工策劃的數據集SciTLDR大約大30倍。

相關鏈接

• 項目主頁：https://github.com/morningmoni/CiteSum
• 論文鏈接：https://arxiv.org/abs/2205.06207
• Hub上的數據集：https://huggingface.co/datasets/nbroad/citesum

📄 許可證

本項目採用CC BY-NC 4.0許可證。