SentencesJudger 是一个基于GRU神经网络的句子判断程序，基本的功能是判断文章中的某一句话是否为一个优美的句子。
python3 -m pip install -U torch ltp
main.py
python3 main.py
| 数据集 | 准确度 |
|---|---|
| train | 96.7% |
| test | 83.5% |
在train.py中选择训练样本、测试样本与输出模型路径，运行train.py即可。训练样本、测试样本为csv文件，格式可参考sample.csv。
目前模型因样本数量过少，判断效果并不理想，持续更新中。
Status: Archive (code is provided as-is, no updates expected) gpt-2 Code and models from the paper "Language Models are Unsupervised Multitask Learner
sentello Sentello is a python script that simulates the anti-evasion and anti-analysis techniques used by malware. For techniques that are difficult t
Feature_CRF_AE Feature_CRF_AE provides a implementation of Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging
CredData is a set of files including credentials in open source projects. CredData includes suspicious lines with manual review results and more information such as credential types for each suspicio
Obfuscation Detection (v1.0) Author: Tim Blazytko Automatically detect control-flow flattening and other state machines Description: Scripts and binar
PAUSE: Positive and Annealed Unlabeled Sentence Embedding Sentence embedding refers to a set of effective and versatile techniques for converting raw
Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervision Training Efficiency We show the training efficiency of our DSLP model b
Introduction XLNet is a new unsupervised language representation learning method based on a novel generalized permutation language modeling objective.
KoPL: 面向知识的推理问答编程语言 安装 | 快速开始 | 文档 KoPL全称 Knowledge oriented Programing Language, 是一个为复杂推理问答而设计的编程语言。我们可以将自然语言问题表示为由基本函数组合而成的KoPL程序，程序运行的结果就是问题的答案。目前，
MicBot MicBot uses Google Translate to speak everyone's chat messages. It can al
TEACh is a dataset of human-human interactive dialogues to complete tasks in a simulated household environment.
Quote extraction for modular journalism (JournalismAI collab 2021)
Chimera: Learning Shared Semantic Space for Speech-to-Text Translation This is a Pytorch implementation for the "Chimera" paper Learning Shared Semant
vec2word Semi-automated vocabulary generation from semantic vector models This script generates a list of potential conlang word forms along with asso
CPM-Pretrain 版本更新记录 为了促进中文自然语言处理研究的发展，本项目提供了大规模预训练语言模型的预训练代码。项目主要基于DeepSpeed、Megatron实现，可以支持数据并行、模型加速、流水并行的代码。 安装 1、首先安装pytorch等基础依赖，再安装APEX以支持fp16。 p
zpy: Synthetic data in Blender. Website • Install • Docs • Examples • CLI • Contribute • Licence Abstract Collecting, labeling, and cleaning data for
LegalQA using SentenceKoBART Implementation of legal QA system based on SentenceKoBART How to train SentenceKoBART Based on Neural Search Engine Jina
News SRU++, a new SRU variant, is released. [tech report] [blog] The experimental code and SRU++ implementation are available on the dev branch which
ja-timex 自然言語で書かれた時間情報表現を抽出/規格化するルールベースの解析器 概要 ja-timex は、現代日本語で書かれた自然文に含まれる時間情報表現を抽出しTIMEX3と呼ばれるアノテーション仕様に変換することで、プログラムが利用できるような形に規格化するルールベースの解析器です。
A Statutory Article Retrieval Dataset in French This repository contains the Belgian Statutory Article Retrieval Dataset (BSARD), as well as the code
16.1k Jan 08, 2023
62 Oct 02, 2022
6 Apr 29, 2022
19 Sep 07, 2022
230 Nov 26, 2022
21 Dec 15, 2022
37 Jan 04, 2023
6k Jan 07, 2023
62 Dec 12, 2022
2 Mar 09, 2022
98 Dec 09, 2022
207 Dec 25, 2022
43 Dec 28, 2022
9 Nov 25, 2022
37 Dec 06, 2022
253 Dec 21, 2022
75 Dec 27, 2022
14 Dec 12, 2022
116 Nov 09, 2022
19 Nov 17, 2022