Google and Stanford University released a new pre-trained model called ELECTRA

Overview

中文说明 | English



GitHub

谷歌与斯坦福大学共同研发的最新预训练模型ELECTRA因其小巧的模型体积以及良好的模型性能受到了广泛关注。 为了进一步促进中文预训练模型技术的研究与发展,哈工大讯飞联合实验室基于官方ELECTRA训练代码以及大规模的中文数据训练出中文ELECTRA预训练模型供大家下载使用。 其中ELECTRA-small模型可与BERT-base甚至其他同等规模的模型相媲美,而参数量仅为BERT-base的1/10。

本项目基于谷歌&斯坦福大学官方的ELECTRA:https://github.com/google-research/electra

其他相关资源:

查看更多哈工大讯飞联合实验室(HFL)发布的资源:https://github.com/ymcui/HFL-Anthology

新闻

2021/7/21 由哈工大SCIR多位学者撰写的《自然语言处理:基于预训练模型的方法》已出版,欢迎大家选购,也可参与我们的赠书活动

2020/12/13 基于大规模法律文书数据,我们训练了面向司法领域的中文ELECTRA系列模型,查看模型下载司法任务效果

2020/10/22 ELECTRA-180g已发布,增加了CommonCrawl的高质量数据,查看模型下载

2020/9/15 我们的论文"Revisiting Pre-Trained Models for Chinese Natural Language Processing"Findings of EMNLP录用为长文。

2020/8/27 哈工大讯飞联合实验室在通用自然语言理解评测GLUE中荣登榜首,查看GLUE榜单新闻

点击这里查看历史新闻

2020/5/29 Chinese ELECTRA-large/small-ex已发布,请查看模型下载,目前只提供Google Drive下载地址,敬请谅解。

2020/4/7 PyTorch用户可通过 🤗 Transformers加载模型,查看快速加载

2020/3/31 本目录发布的模型已接入飞桨PaddleHub,查看快速加载

2020/3/25 Chinese ELECTRA-small/base已发布,请查看模型下载

内容导引

章节 描述
简介 介绍ELECTRA基本原理
模型下载 中文ELECTRA预训练模型下载
快速加载 介绍了如何使用 🤗 TransformersPaddleHub快速加载模型
基线系统效果 中文基线系统效果:阅读理解、文本分类等
使用方法 模型的详细使用方法
FAQ 常见问题答疑
引用 本目录的技术报告

简介

ELECTRA提出了一套新的预训练框架,其中包括两个部分:GeneratorDiscriminator

  • Generator: 一个小的MLM,在[MASK]的位置预测原来的词。Generator将用来把输入文本做部分词的替换。
  • Discriminator: 判断输入句子中的每个词是否被替换,即使用Replaced Token Detection (RTD)预训练任务,取代了BERT原始的Masked Language Model (MLM)。需要注意的是这里并没有使用Next Sentence Prediction (NSP)任务。

在预训练阶段结束之后,我们只使用Discriminator作为下游任务精调的基模型。

更详细的内容请查阅ELECTRA论文:ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

模型下载

本目录中包含以下模型,目前仅提供TensorFlow版本权重。

  • ELECTRA-large, Chinese: 24-layer, 1024-hidden, 16-heads, 324M parameters
  • ELECTRA-base, Chinese: 12-layer, 768-hidden, 12-heads, 102M parameters
  • ELECTRA-small-ex, Chinese: 24-layer, 256-hidden, 4-heads, 25M parameters
  • ELECTRA-small, Chinese: 12-layer, 256-hidden, 4-heads, 12M parameters

大语料版(新版,180G数据)

模型简称 Google下载 讯飞云下载 压缩包大小
ELECTRA-180g-large, Chinese TensorFlow TensorFlow(密码Yfcy) 1G
ELECTRA-180g-base, Chinese TensorFlow TensorFlow(密码Xcvm) 383M
ELECTRA-180g-small-ex, Chinese TensorFlow TensorFlow(密码GUdp) 92M
ELECTRA-180g-small, Chinese TensorFlow TensorFlow(密码qsHj) 46M

基础版(原版,20G数据)

模型简称 Google下载 讯飞云下载 压缩包大小
ELECTRA-large, Chinese TensorFlow (待补充) 1G
ELECTRA-base, Chinese TensorFlow TensorFlow(密码3VQu) 383M
ELECTRA-small-ex, Chinese TensorFlow (待补充) 92M
ELECTRA-small, Chinese TensorFlow TensorFlow(密码wm2E) 46M

司法领域版(new)

模型简称 Google下载 讯飞云下载 压缩包大小
legal-ELECTRA-large, Chinese TensorFlow TensorFlow(密码7f7b) 1G
legal-ELECTRA-base, Chinese TensorFlow TensorFlow(密码7f7b) 383M
legal-ELECTRA-small, Chinese TensorFlow TensorFlow(密码7f7b) 46M

PyTorch/TF2版本

如需PyTorch版本,请自行通过 🤗 Transformers提供的转换脚本convert_electra_original_tf_checkpoint_to_pytorch.py进行转换。如需配置文件可进入到本目录下的config文件夹中查找。

python transformers/src/transformers/convert_electra_original_tf_checkpoint_to_pytorch.py \
--tf_checkpoint_path ./path-to-large-model/ \
--config_file ./path-to-large-model/discriminator.json \
--pytorch_dump_path ./path-to-output/model.bin \
--discriminator_or_generator discriminator

或者通过huggingface官网直接下载PyTorch版权重:https://huggingface.co/hfl

方法:点击任意需要下载的model → 拉到最下方点击"List all files in model" → 在弹出的小框中下载bin和json文件。

使用须知

中国大陆境内建议使用讯飞云下载点,境外用户建议使用谷歌下载点。 以TensorFlow版ELECTRA-small, Chinese为例,下载完毕后对zip文件进行解压得到如下文件。

chinese_electra_small_L-12_H-256_A-4.zip
    |- electra_small.data-00000-of-00001    # 模型权重
    |- electra_small.meta                   # 模型meta信息
    |- electra_small.index                  # 模型index信息
    |- vocab.txt                            # 词表
    |- discriminator.json                   # 配置文件:discriminator(若没有可从本repo中的config目录获取)
    |- generator.json                       # 配置文件:generator(若没有可从本repo中的config目录获取)

训练细节

我们采用了大规模中文维基以及通用文本训练了ELECTRA模型,总token数达到5.4B,与RoBERTa-wwm-ext系列模型一致。词表方面沿用了谷歌原版BERT的WordPiece词表,包含21,128个token。其他细节和超参数如下(未提及的参数保持默认):

  • ELECTRA-large: 24层,隐层1024,16个注意力头,学习率1e-4,batch96,最大长度512,训练2M步
  • ELECTRA-base: 12层,隐层768,12个注意力头,学习率2e-4,batch256,最大长度512,训练1M步
  • ELECTRA-small-ex: 24层,隐层256,4个注意力头,学习率5e-4,batch384,最大长度512,训练2M步
  • ELECTRA-small: 12层,隐层256,4个注意力头,学习率5e-4,batch1024,最大长度512,训练1M步

快速加载

使用Huggingface-Transformers

Huggingface-Transformers 2.8.0版本已正式支持ELECTRA模型,可通过如下命令调用。

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModel.from_pretrained(MODEL_NAME) 

其中MODEL_NAME对应列表如下:

模型名 组件 MODEL_NAME
ELECTRA-180g-large, Chinese discriminator hfl/chinese-electra-180g-large-discriminator
ELECTRA-180g-large, Chinese generator hfl/chinese-electra-180g-large-generator
ELECTRA-180g-base, Chinese discriminator hfl/chinese-electra-180g-base-discriminator
ELECTRA-180g-base, Chinese generator hfl/chinese-electra-180g-base-generator
ELECTRA-180g-small-ex, Chinese discriminator hfl/chinese-electra-180g-small-ex-discriminator
ELECTRA-180g-small-ex, Chinese generator hfl/chinese-electra-180g-small-ex-generator
ELECTRA-180g-small, Chinese discriminator hfl/chinese-electra-180g-small-discriminator
ELECTRA-180g-small, Chinese generator hfl/chinese-electra-180g-small-generator
ELECTRA-large, Chinese discriminator hfl/chinese-electra-large-discriminator
ELECTRA-large, Chinese generator hfl/chinese-electra-large-generator
ELECTRA-base, Chinese discriminator hfl/chinese-electra-base-discriminator
ELECTRA-base, Chinese generator hfl/chinese-electra-base-generator
ELECTRA-small-ex, Chinese discriminator hfl/chinese-electra-small-ex-discriminator
ELECTRA-small-ex, Chinese generator hfl/chinese-electra-small-ex-generator
ELECTRA-small, Chinese discriminator hfl/chinese-electra-small-discriminator
ELECTRA-small, Chinese generator hfl/chinese-electra-small-generator

司法领域版本:

模型名 组件 MODEL_NAME
legal-ELECTRA-large, Chinese discriminator hfl/chinese-legal-electra-large-discriminator
legal-ELECTRA-large, Chinese generator hfl/chinese-legal-electra-large-generator
legal-ELECTRA-base, Chinese discriminator hfl/chinese-legal-electra-base-discriminator
legal-ELECTRA-base, Chinese generator hfl/chinese-legal-electra-base-generator
legal-ELECTRA-small, Chinese discriminator hfl/chinese-legal-electra-small-discriminator
legal-ELECTRA-small, Chinese generator hfl/chinese-legal-electra-small-generator

使用PaddleHub

依托PaddleHub,我们只需一行代码即可完成模型下载安装,十余行代码即可完成文本分类、序列标注、阅读理解等任务。

import paddlehub as hub
module = hub.Module(name=MODULE_NAME)

其中MODULE_NAME对应列表如下:

模型名 MODULE_NAME
ELECTRA-base, Chinese chinese-electra-base
ELECTRA-small, Chinese chinese-electra-small

基线系统效果

我们将ELECTRA-small/baseBERT-baseBERT-wwmBERT-wwm-extRoBERTa-wwm-extRBT3进行了效果对比,包括以下六个任务:

对于ELECTRA-small/base模型,我们使用原论文默认的3e-41e-4的学习率。 需要注意的是,我们没有针对任何任务进行参数精调,所以通过调整学习率等超参数可能获得进一步性能提升。 为了保证结果的可靠性,对于同一模型,我们使用不同随机种子训练10遍,汇报模型性能的最大值和平均值(括号内为平均值)。

简体中文阅读理解:CMRC 2018

CMRC 2018数据集是哈工大讯飞联合实验室发布的中文机器阅读理解数据。 根据给定问题,系统需要从篇章中抽取出片段作为答案,形式与SQuAD相同。 评价指标为:EM / F1

模型 开发集 测试集 挑战集 参数量
BERT-base 65.5 (64.4) / 84.5 (84.0) 70.0 (68.7) / 87.0 (86.3) 18.6 (17.0) / 43.3 (41.3) 102M
BERT-wwm 66.3 (65.0) / 85.6 (84.7) 70.5 (69.1) / 87.4 (86.7) 21.0 (19.3) / 47.0 (43.9) 102M
BERT-wwm-ext 67.1 (65.6) / 85.7 (85.0) 71.4 (70.0) / 87.7 (87.0) 24.0 (20.0) / 47.3 (44.6) 102M
RoBERTa-wwm-ext 67.4 (66.5) / 87.2 (86.5) 72.6 (71.4) / 89.4 (88.8) 26.2 (24.6) / 51.0 (49.1) 102M
RBT3 57.0 / 79.0 62.2 / 81.8 14.7 / 36.2 38M
ELECTRA-small 63.4 (62.9) / 80.8 (80.2) 67.8 (67.4) / 83.4 (83.0) 16.3 (15.4) / 37.2 (35.8) 12M
ELECTRA-180g-small 63.8 / 82.7 68.5 / 85.2 15.1 / 35.8 12M
ELECTRA-small-ex 66.4 / 82.2 71.3 / 85.3 18.1 / 38.3 25M
ELECTRA-180g-small-ex 68.1 / 85.1 71.8 / 87.2 20.6 / 41.7 25M
ELECTRA-base 68.4 (68.0) / 84.8 (84.6) 73.1 (72.7) / 87.1 (86.9) 22.6 (21.7) / 45.0 (43.8) 102M
ELECTRA-180g-base 69.3 / 87.0 73.1 / 88.6 24.0 / 48.6 102M
ELECTRA-large 69.1 / 85.2 73.9 / 87.1 23.0 / 44.2 324M
ELECTRA-180g-large 68.5 / 86.2 73.5 / 88.5 21.8 / 42.9 324M

繁体中文阅读理解:DRCD

DRCD数据集由中国台湾台达研究院发布,其形式与SQuAD相同,是基于繁体中文的抽取式阅读理解数据集。 评价指标为:EM / F1

模型 开发集 测试集 参数量
BERT-base 83.1 (82.7) / 89.9 (89.6) 82.2 (81.6) / 89.2 (88.8) 102M
BERT-wwm 84.3 (83.4) / 90.5 (90.2) 82.8 (81.8) / 89.7 (89.0) 102M
BERT-wwm-ext 85.0 (84.5) / 91.2 (90.9) 83.6 (83.0) / 90.4 (89.9) 102M
RoBERTa-wwm-ext 86.6 (85.9) / 92.5 (92.2) 85.6 (85.2) / 92.0 (91.7) 102M
RBT3 76.3 / 84.9 75.0 / 83.9 38M
ELECTRA-small 79.8 (79.4) / 86.7 (86.4) 79.0 (78.5) / 85.8 (85.6) 12M
ELECTRA-180g-small 83.5 / 89.2 82.9 / 88.7 12M
ELECTRA-small-ex 84.0 / 89.5 83.3 / 89.1 25M
ELECTRA-180g-small-ex 87.3 / 92.3 86.5 / 91.3 25M
ELECTRA-base 87.5 (87.0) / 92.5 (92.3) 86.9 (86.6) / 91.8 (91.7) 102M
ELECTRA-180g-base 89.6 / 94.2 88.9 / 93.7 102M
ELECTRA-large 88.8 / 93.3 88.8 / 93.6 324M
ELECTRA-180g-large 90.1 / 94.8 90.5 / 94.7 324M

自然语言推断:XNLI

在自然语言推断任务中,我们采用了XNLI数据,需要将文本分成三个类别:entailmentneutralcontradictory。 评价指标为:Accuracy

模型 开发集 测试集 参数量
BERT-base 77.8 (77.4) 77.8 (77.5) 102M
BERT-wwm 79.0 (78.4) 78.2 (78.0) 102M
BERT-wwm-ext 79.4 (78.6) 78.7 (78.3) 102M
RoBERTa-wwm-ext 80.0 (79.2) 78.8 (78.3) 102M
RBT3 72.2 72.3 38M
ELECTRA-small 73.3 (72.5) 73.1 (72.6) 12M
ELECTRA-180g-small 74.6 74.6 12M
ELECTRA-small-ex 75.4 75.8 25M
ELECTRA-180g-small-ex 76.5 76.6 25M
ELECTRA-base 77.9 (77.0) 78.4 (77.8) 102M
ELECTRA-180g-base 79.6 79.5 102M
ELECTRA-large 81.5 81.0 324M
ELECTRA-180g-large 81.2 80.4 324M

情感分析:ChnSentiCorp

在情感分析任务中,二分类的情感分类数据集ChnSentiCorp。 评价指标为:Accuracy

模型 开发集 测试集 参数量
BERT-base 94.7 (94.3) 95.0 (94.7) 102M
BERT-wwm 95.1 (94.5) 95.4 (95.0) 102M
BERT-wwm-ext 95.4 (94.6) 95.3 (94.7) 102M
RoBERTa-wwm-ext 95.0 (94.6) 95.6 (94.8) 102M
RBT3 92.8 92.8 38M
ELECTRA-small 92.8 (92.5) 94.3 (93.5) 12M
ELECTRA-180g-small 94.1 93.6 12M
ELECTRA-small-ex 92.6 93.6 25M
ELECTRA-180g-small-ex 92.8 93.4 25M
ELECTRA-base 93.8 (93.0) 94.5 (93.5) 102M
ELECTRA-180g-base 94.3 94.8 102M
ELECTRA-large 95.2 95.3 324M
ELECTRA-180g-large 94.8 95.2 324M

句对分类:LCQMC

以下两个数据集均需要将一个句对进行分类,判断两个句子的语义是否相同(二分类任务)。

LCQMC由哈工大深圳研究生院智能计算研究中心发布。 评价指标为:Accuracy

模型 开发集 测试集 参数量
BERT 89.4 (88.4) 86.9 (86.4) 102M
BERT-wwm 89.4 (89.2) 87.0 (86.8) 102M
BERT-wwm-ext 89.6 (89.2) 87.1 (86.6) 102M
RoBERTa-wwm-ext 89.0 (88.7) 86.4 (86.1) 102M
RBT3 85.3 85.1 38M
ELECTRA-small 86.7 (86.3) 85.9 (85.6) 12M
ELECTRA-180g-small 86.6 85.8 12M
ELECTRA-small-ex 87.5 86.0 25M
ELECTRA-180g-small-ex 87.6 86.3 25M
ELECTRA-base 90.2 (89.8) 87.6 (87.3) 102M
ELECTRA-180g-base 90.2 87.1 102M
ELECTRA-large 90.7 87.3 324M
ELECTRA-180g-large 90.3 87.3 324M

句对分类:BQ Corpus

BQ Corpus由哈工大深圳研究生院智能计算研究中心发布,是面向银行领域的数据集。 评价指标为:Accuracy

模型 开发集 测试集 参数量
BERT 86.0 (85.5) 84.8 (84.6) 102M
BERT-wwm 86.1 (85.6) 85.2 (84.9) 102M
BERT-wwm-ext 86.4 (85.5) 85.3 (84.8) 102M
RoBERTa-wwm-ext 86.0 (85.4) 85.0 (84.6) 102M
RBT3 84.1 83.3 38M
ELECTRA-small 83.5 (83.0) 82.0 (81.7) 12M
ELECTRA-180g-small 83.3 82.1 12M
ELECTRA-small-ex 84.0 82.6 25M
ELECTRA-180g-small-ex 84.6 83.4 25M
ELECTRA-base 84.8 (84.7) 84.5 (84.0) 102M
ELECTRA-180g-base 85.8 84.5 102M
ELECTRA-large 86.7 85.1 324M
ELECTRA-180g-large 86.4 85.4 324M

司法任务效果

我们使用CAIL 2018司法评测的罪名预测数据对司法ELECTRA进行了测试。small/base/large学习率分别为:5e-4/3e-4/1e-4。 评价指标为:Accuracy

模型 开发集 测试集 参数量
ELECTRA-small 78.84 76.35 12M
legal-ELECTRA-small 79.60 77.03 12M
ELECTRA-base 80.94 78.41 102M
legal-ELECTRA-base 81.71 79.17 102M
ELECTRA-large 81.53 78.97 324M
legal-ELECTRA-large 82.60 79.89 324M

使用方法

用户可以基于已发布的上述中文ELECTRA预训练模型进行下游任务精调。 在这里我们只介绍最基本的用法,更详细的用法请参考ELECTRA官方介绍

本例中,我们使用ELECTRA-small模型在CMRC 2018任务上进行精调,相关步骤如下。假设,

  • data-dir:工作根目录,可按实际情况设置。
  • model-name:模型名称,本例中为electra-small
  • task-name:任务名称,本例中为cmrc2018。本目录中的代码已适配了以上六个中文任务,task-name分别为cmrc2018drcdxnlichnsenticorplcqmcbqcorpus

第一步:下载预训练模型并解压

模型下载章节中,下载ELECTRA-small模型,并解压至${data-dir}/models/${model-name}。 该目录下应包含electra_model.*vocab.txtcheckpoint,共计5个文件。

第二步:准备任务数据

下载CMRC 2018训练集和开发集,并重命名为train.jsondev.json。 将两个文件放到${data-dir}/finetuning_data/${task-name}

第三步:运行训练命令

python run_finetuning.py \
    --data-dir ${data-dir} \
    --model-name ${model-name} \
    --hparams params_cmrc2018.json

其中data-dirmodel-name在上面已经介绍。hparams是一个JSON词典,在本例中的params_cmrc2018.json包含了精调相关超参数,例如:

{
    "task_names": ["cmrc2018"],
    "max_seq_length": 512,
    "vocab_size": 21128,
    "model_size": "small",
    "do_train": true,
    "do_eval": true,
    "write_test_outputs": true,
    "num_train_epochs": 2,
    "learning_rate": 3e-4,
    "train_batch_size": 32,
    "eval_batch_size": 32,
}

在上述JSON文件中,我们只列举了最重要的一些参数,完整参数列表请查阅configure_finetuning.py

运行完毕后,

  1. 对于阅读理解任务,生成的预测JSON数据cmrc2018_dev_preds.json保存在${data-dir}/results/${task-name}_qa/。可以调用外部评测脚本来得到最终评测结果,例如:python cmrc2018_drcd_evaluate.py dev.json cmrc2018_dev_preds.json
  2. 对于分类任务,相关accuracy信息会直接打印在屏幕,例如:xnli: accuracy: 72.5 - loss: 0.67

FAQ

Q: 在下游任务精调的时候ELECTRA模型的学习率怎么设置?
A: 我们建议使用原论文使用的学习率作为初始基线(small是3e-4,base是1e-4)然后适当增减学习率进行调试。 需要注意的是,相比BERT、RoBERTa一类的模型来说ELECTRA的学习率要相对大一些。

Q: 有没有PyTorch版权重?
A: 有,模型下载

Q: 预训练用的数据能共享一下吗?
A: 很遗憾,不可以。

Q: 未来计划?
A: 敬请关注。

引用

如果本目录中的内容对你的研究工作有所帮助,欢迎在论文中引用下述技术报告。

@inproceedings{cui-etal-2020-revisiting,
    title = "Revisiting Pre-Trained Models for {C}hinese Natural Language Processing",
    author = "Cui, Yiming  and
      Che, Wanxiang  and
      Liu, Ting  and
      Qin, Bing  and
      Wang, Shijin  and
      Hu, Guoping",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.findings-emnlp.58",
    pages = "657--668",
}

关注我们

欢迎关注哈工大讯飞联合实验室官方微信公众号,了解最新的技术动态。

qrcode.png

问题反馈

Before you submit an issue:

  • You are advised to read FAQ first before you submit an issue.
  • Repetitive and irrelevant issues will be ignored and closed by [stable-bot](stale · GitHub Marketplace). Thank you for your understanding and support.
  • We cannot acommodate EVERY request, and thus please bare in mind that there is no guarantee that your request will be met.
  • Always be polite when you submit an issue.
Owner
Yiming Cui
NLP Researcher. Mainly interested in Machine Reading Comprehension, Question Answering, Pre-trained Language Model, etc.
Yiming Cui
NeuTex: Neural Texture Mapping for Volumetric Neural Rendering

NeuTex: Neural Texture Mapping for Volumetric Neural Rendering Paper: https://arxiv.org/abs/2103.00762 Running Run on the provided DTU scene cd run ba

Fanbo Xiang 68 Jan 06, 2023
HAN2HAN : Hangul Font Generation

HAN2HAN : Hangul Font Generation

Changwoo Lee 36 Dec 28, 2022
Multiple implementations for abstractive text summurization , using google colab

Text Summarization models if you are able to endorse me on Arxiv, i would be more than glad https://arxiv.org/auth/endorse?x=FRBB89 thanks This repo i

463 Dec 26, 2022
Using Bert as the backbone model for lime, designed for NLP task explanation (sentence pair text classification task)

Lime Comparing deep contextualized model for sentences highlighting task. In addition, take the classic explanation model "LIME" with bert-base model

JHJu 2 Jan 18, 2022
Script to download some free japanese lessons in portuguse from NHK

Nihongo_nhk This is a script to download some free japanese lessons in portuguese from NHK. It can be executed by installing the packages with: pip in

Matheus Alves 2 Jan 06, 2022
Scene Text Retrieval via Joint Text Detection and Similarity Learning

This is the code of "Scene Text Retrieval via Joint Text Detection and Similarity Learning". For more details, please refer to our CVPR2021 paper.

79 Nov 29, 2022
nlp-tutorial is a tutorial for who is studying NLP(Natural Language Processing) using Pytorch

nlp-tutorial is a tutorial for who is studying NLP(Natural Language Processing) using Pytorch. Most of the models in NLP were implemented with less than 100 lines of code.(except comments or blank li

Tae-Hwan Jung 11.9k Jan 08, 2023
Predicting the usefulness of reviews given the review text and metadata surrounding the reviews.

Predicting Yelp Review Quality Table of Contents Introduction Motivation Goal and Central Questions The Data Data Storage and ETL EDA Data Pipeline Da

Jeff Johannsen 3 Nov 27, 2022
A number of methods in order to perform Natural Language Processing on live data derived from Twitter

A number of methods in order to perform Natural Language Processing on live data derived from Twitter

1 Nov 24, 2021
Simple and efficient RevNet-Library with DeepSpeed support

RevLib Simple and efficient RevNet-Library with DeepSpeed support Features Half the constant memory usage and faster than RevNet libraries Less memory

Lucas Nestler 112 Dec 05, 2022
A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP

A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP

420 Dec 28, 2022
Transformer related optimization, including BERT, GPT

This repository provides a script and recipe to run the highly optimized transformer-based encoder and decoder component, and it is tested and maintained by NVIDIA.

NVIDIA Corporation 1.7k Jan 04, 2023
Prithivida 690 Jan 04, 2023
Code and data accompanying Natural Language Processing with PyTorch

Natural Language Processing with PyTorch Build Intelligent Language Applications Using Deep Learning By Delip Rao and Brian McMahan Welcome. This is a

Joostware 1.8k Jan 01, 2023
Malaya-Speech is a Speech-Toolkit library for bahasa Malaysia, powered by Deep Learning Tensorflow.

Malaya-Speech is a Speech-Toolkit library for bahasa Malaysia, powered by Deep Learning Tensorflow. Documentation Proper documentation is available at

HUSEIN ZOLKEPLI 151 Jan 05, 2023
A library for end-to-end learning of embedding index and retrieval model

Poeem Poeem is a library for efficient approximate nearest neighbor (ANN) search, which has been widely adopted in industrial recommendation, advertis

54 Dec 21, 2022
neural network based speaker embedder

Content What is deepaudio-speaker? Installation Get Started Model Architecture How to contribute to deepaudio-speaker? Acknowledge What is deepaudio-s

20 Dec 29, 2022
This repo stores the codes for topic modeling on palliative care journals.

This repo stores the codes for topic modeling on palliative care journals. Data Preparation You first need to download the journal papers. bash 1_down

3 Dec 20, 2022
A natural language modeling framework based on PyTorch

Overview PyText is a deep-learning based NLP modeling framework built on PyTorch. PyText addresses the often-conflicting requirements of enabling rapi

Facebook Research 6.4k Dec 27, 2022
ttslearn: Library for Pythonで学ぶ音声合成 (Text-to-speech with Python)

ttslearn: Library for Pythonで学ぶ音声合成 (Text-to-speech with Python) 日本語は以下に続きます (Japanese follows) English: This book is written in Japanese and primaril

Ryuichi Yamamoto 189 Dec 29, 2022