首页
学习
活动
专区
圈层
工具
发布
    • 综合排序
    • 最热优先
    • 最新优先
    时间不限
  • 来自专栏人工智能极简应用

    【人工智能】Transformers之Pipeline(十四):问答(question-answering

    共计覆盖32万个模型 今天介绍NLP自然语言处理的第二篇:问答(question-answering),在huggingface库内有1.2万个问答(question-answering)模型,最典型的是在 二、问答(question-answering) 2.1 概述 问答模型可以从给定的文本中检索问题的答案,这对于在文档中搜索答案非常有用。一些问答模型可以在没有上下文的情况下生成答案! = "2" from transformers import pipeline qa = pipeline(model="deepset/roberta-base-squad2", task="question-answering 三、总结 本文对transformers之pipeline的问答(question-answering)从概述、技术原理、pipeline参数、pipeline实战、模型排名等方面进行介绍,读者可以基于 pipeline使用文中的2行代码极简的使用NLP中的问答(question-answering)模型。

    60310编辑于 2024-09-03
  • 来自专栏JadePeng的技术博客

    Transformers Optimum 使用

    = ORTModelForQuestionAnswering.from_pretrained("optimum/roberta-base-squad2") onnx_qa = pipeline("question-answering AutoTokenizer.from_pretrained(model_id) model = AutoModelForQuestionAnswering.from_pretrained(model_id) pipeline_qa = pipeline('question-answering provider="CUDAExecutionProvider") ort_model_qa = ortpipeline( "question-answering ORTModelForQuestionAnswering.from_pretrained( save_dir, file_name="model-optimized.onnx") opt_onnx_qa = ortpipeline("question-answering

    1.4K41编辑于 2022-12-09
  • 来自专栏NLP/KG

    Gradio入门到进阶全网最详细教程[二]:快速搭建AI算法可视化部署演示(侧重参数详解和案例实践)

    transformers相关包from transformers import *#通过Interface加载pipeline并启动服务gr.Interface.from_pipeline(pipeline("question-answering spm=1001.2014.3001.5482)"gr.Interface.from_pipeline( pipeline("question-answering", model="uer/roberta-base-chinese-extractive-qa qa = pipeline("question-answering", model="uer/roberta-base-chinese-extractive-qa")def custom_predict spm=1001.2014.3001.5482)"qa = pipeline("question-answering", model="uer/roberta-base-chinese-extractive-qa article = "感兴趣的小伙伴可以阅读[Transformers实用指南](https://zhuanlan.zhihu.com/p/548336726)"#预测函数qa = pipeline("question-answering

    1.9K30编辑于 2023-04-26
  • 来自专栏NLP/KG

    Gradio入门到进阶全网最详细教程[二]:快速搭建AI算法可视化部署演示(侧重参数详解和案例实践)

    transformers相关包 from transformers import * #通过Interface加载pipeline并启动服务 gr.Interface.from_pipeline(pipeline("question-answering spm=1001.2014.3001.5482)" gr.Interface.from_pipeline( pipeline("question-answering", model="uer/ qa = pipeline("question-answering", model="uer/roberta-base-chinese-extractive-qa") def custom_predict spm=1001.2014.3001.5482)" qa = pipeline("question-answering", model="uer/roberta-base-chinese-extractive-qa article = "感兴趣的小伙伴可以阅读[Transformers实用指南](https://zhuanlan.zhihu.com/p/548336726)" #预测函数 qa = pipeline("question-answering

    2.6K52编辑于 2023-05-01
  • 来自专栏超级架构师

    IBM Research: WatsonPaths

    Explore the WatsonPaths interface Scenario analysis For WatsonPaths, in the background we use Watson's question-answering Using Watson’s question-answering abilities, WatsonPaths can examine the scenario from many angles, working

    1.8K70发布于 2018-04-09
  • 来自专栏企鹅号快讯

    Job Prospects of AI

    security of password verification Intelligent customer service智能客服 To build the financial sector dedicated question-answering

    92930发布于 2018-03-01
  • 来自专栏DeepHub IMBA

    用PyTorch和预训练的Transformers 创建问答系统

    为了构建问答管道,我们使用如下代码: question_answering = pipeline(“question-answering”) 这将在后台创建一个预先训练的问题回答模型以及它的标记器。 现在,根据模型文档,我们可以通过指定模型和标记器参数来直接在管道中构建模型,如下所示: question_answering = pipeline("question-answering", model

    1.7K12发布于 2021-02-12
  • 来自专栏人工智能头条

    Yann LeCun:157页PPT揭示深度学习的局限性

    Many tasks in natural language understanding, such as question-answering, require a way to temporarily

    41560发布于 2018-06-05
  • 来自专栏我还不懂对话

    NER的过去、现在和未来综述-未来

    Using BARTImproving Language Models by Retrieving from Trillions of TokensWebGPT: Browser-assisted question-answering

    2.1K41编辑于 2022-10-08
  • 来自专栏算法工程师的养成之路

    自然语言处理(一)NLP概述

    (Information Retrieval) 信息抽取(Information Extraction) 自动文摘(Automatic summarization/abstracting) 问答系统(Question-Answering

    1.3K10发布于 2019-01-11
  • 来自专栏AI算法与图像处理

    CVPR2022论文速递(2022.5.31)!共9篇!

    Code: None From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering

    58230编辑于 2022-09-02
  • 来自专栏HyperAI超神经

    用 BERT 精简版 DistilBERT+TF.js,提升问答系统 2 倍性能

    memory used by the result tensor since we don’t need it anymore NPM 问答包 https://www.npmjs.com/package/question-answering 用于推理的 TensorFlow.js 以及用于词条化的分词器,我们可以在 NPM 包中提供颇为简单而又功能强大的公共 API,从而实现当初的既定目标: import { QAClient } from "question-answering "; // If using Typescript or Babel // const { QAClient } = require("question-answering"); // If using

    1.5K30发布于 2020-08-27
  • 来自专栏人工智能极简应用

    【人工智能】Transformers之Pipeline(概述):30w+大模型极简应用

    "question-answering":将返回一个QuestionAnsweringPipeline。 "summarization":将返回一个SummarizationPipeline。 bert-large-cased-finetuned-conll03-english", "f2482bf"), }, }, "type": "text", }, "question-answering

    1.5K10编辑于 2024-08-13
  • 来自专栏大鹅专栏:大数据到机器学习

    NLP任务汇总简介与理解

    image.png (6)问答系统(Question-Answering Systerm) 针对用户提出的问题,系统给出相应的答案。 Machine Translation):通过计算机自动化的把一种语言翻译成另外一种语言 文本摘要(Text summarization/Simplication):对较长文本进行内容梗概的提取 问答系统(Question-Answering

    4.7K63发布于 2021-10-06
  • 来自专栏云社区活动

    解构语义分析:核心算法揭秘与实战

    from transformers import pipelineqa_model = pipeline("question-answering", model="distilbert-base-cased-distilled-squad

    53010编辑于 2025-03-21
  • 来自专栏机器之心

    学界 | 详解微软意识网络架构:具有可解释性的新型类脑AI系统

    微软研究院最新的一篇论文《Deep Learning of Grammatically-Interpretable Representations Through Question-Answering》 论文:Deep Learning of Grammatically-Interpretable Representations Through Question-Answering 论文链接:http:

    1.4K60发布于 2018-05-08
  • 来自专栏NewBeeNLP

    大模型的涌现能力 (Emergent Abilities of LLM)

    比如在closed-book question-answering可能需要模型有更多的参数去记忆尝试知识。 衡量emergent abilities的evaluation metrics也值得探究。

    1.4K31编辑于 2023-08-29
  • 来自专栏机器学习实践二三事

    NLP常用数据集

    For more, see the post: Datasets: How can I get corpus of a question-answering website like Quora or

    1.3K101发布于 2018-01-02
  • 黑马博学谷 AI大模型训练营一期

    Flask, request, jsonifyfrom transformers import pipelineapp = Flask(__name__)qa_pipeline = pipeline('question-answering

    69810编辑于 2024-07-20
  • 来自专栏AI+运维:智能化运维的未来

    运维老司机的福音——深度学习如何革新运维知识管理?

    看看下面的代码示例:from transformers import pipeline# 载入预训练的问答模型qa_pipeline = pipeline("question-answering", model

    28710编辑于 2025-05-27
领券