Meiling_up

本文记录了复现PromptStealer论文的环境配置过程。为避免网络问题，使用huggingface镜像预先下载了论文中使用的lexica_dataset数据集。

本篇博客分享了多种图像溯源方法的复现经验，涵盖Close-set Attribution、Open-set Attribution和Single-Model Attribution三大类。具体方法包括RepMix、De-Fake、DNA-Net、POSE、OCC-CLIP和LatentTracer。文章详细介绍了每种方法的环境配置、代码适配以及数据集处理中的常见问题和解决方案。

本篇博客记录如何使用 LLaMA-Factory 微调 Llama3-8B-Chinese-Chat 完成知识问答任务，并介绍相应报错的解决方法。

本篇博客分享国家自然科学基金申报书撰写心得。

本篇博客记录 20250220 MAS Lab 第一次大组会要点。

本篇博客记录 20240831 MAS Lab 第一次大组会要点。

Computer Journal 期刊投稿经验分享

本文分享CSC联培博士生 - 导师推荐信撰写要点

2023年11月15日，下午13:00-15:00，实验室组内召开AIGC研究讨论会。本次会议收获颇丰，此篇博客记录本人对本次会议比较感兴趣的内容。

碎片笔记｜AIGC核心技术综述

本文介绍大模型攻防领域中「Prompt提示词攻击」的相关知识。

碎片笔记 | 大模型攻防简报

碎片笔记｜可训练&非自回归解码策略

本文介绍网络空间安全领域的几个“安全”概念。

一点思考｜漫谈 AI 中的「反馈」机制

本文为大家介绍多媒体与AI安全研究同行值得关注的一个非营利性质公众号——「隐者联盟」。

前沿探索｜关于 AIGC 的「幻觉/梦游」问题

碎片笔记｜图数据与图神经网络介绍

深度学习模型训练&验证&测试流程

学术笔记｜科技论文写作常用拉丁语词汇总结

博士毕业答辩流程 & 注意事项

pytorch使用小技巧总结。

from __future__ import divisionimport randomimport nltkfrom bs4 import BeautifulSoupfrom nltk.corpus import brown, words, udhr, gutenberg, genesis, abc, wordnet as wnfrom urllib.request import urlopenimport pycountry# 1string = 'colorness'new_s.

import pprintimport nltkimport pylabfrom nltk.corpus import brown# 1lst1 = 'British Left Waffles on Falkland Islands'lst2 = 'Juvenile Court to Try Shooting Defendant'text1 = nltk.word_tokenize(lst1)print(nltk.pos_tag(text1))text2 = nltk.word_tok.

import nltkfrom nltk.corpus import gutenberg, webtext, nps_chat, brown, reuters, inaugural, udhrprint(nltk.corpus.gutenberg.fileids())emma = nltk.corpus.gutenberg.words('austen-emma.txt')print(emma, len(emma))emma = nltk.Text(gutenberg.words('aust.

import nltkfrom nltk.corpus import brown, treebankfrom operator import itemgetterfrom nltk.tbl import demo as brill_demotext = nltk.word_tokenize("And now for something completely different")print(nltk.pos_tag(text))nltk.help.upenn_tagset('RB')t.

import nltkfrom nltk.corpus import names, senseval, movie_reviews, nps_chat, brown, ppattachimport random# 2# Gender Identificationnames = ([(name, 'male') for name in names.words('male.txt')] + [(name, 'female') for name in names.words('f.

Natural Language Processing with Python– Analyzing Text with the Natural Language ToolkitSteven Bird, Ewan Klein, and Edward LoperThis version of the NLTK book is updated for Python 3 and NLTK 3.thelatest versionof the nltk book is available at...

3.1 The Test SetWhat's worse, because of the call torandom.shuffle(), the test set contains sentences that are taken from the same documents that were used for training.

import nltkfrom nltk import load_parser# Example 9.1kim = {'CAT': 'NP', 'ORTH': 'Kim', 'REF': 'k'}chase = {'CAT': 'V', 'ORTH': 'chased', 'REL': 'chase'}chase['AGT'] = 'sbj'chase['PAT'] = 'obj'lee = {'CAT': 'NP', 'ORTH': 'Lee', 'REF': 'l'}sent = .

在使用python3.7运行Natural Language Processing with Python Chapter 5 的最后一个示例from nltk.tbl import demo as brill_demobrill_demo.demo()print(open("errors.out").read())时， 出现如下错误：Traceback (most recent call last): File "E:/Python Practice/NLP/Chapter5.py

import nltk# 1grammar = nltk.data.load('9_1_1.fcfg')print(grammar)tokens_1 = "I am happy".split()tokens_2 = "she is happy".split()tokens_3 = "she am happy".split()parser = nltk.load_parser('9_1_1.fcfg')for tree in parser.parse(tokens_1): pri.

import nltkfrom nltk import refrom bs4 import BeautifulSoupimport csvfrom collections import Counterfrom collections import defaultdictfrom nltk.corpus import toolboximport sysfrom nltk.util import elementtree_indentfrom xml.etree.ElementTree imp.

from random import randomimport matplotlibimport networkx as nximport nltkfrom nltk import ngrams, refrom nltk.corpus import state_union, swadesh, cmudict, wordnet as wn, shakespeare# 1help(str)help(list)help(tuple)# 2list1 = [1, 2, 3, 4]tu.

import nltkfrom nltk import chunk, treefrom nltk.corpus import conll2000, brown, treebank_chunk, treebankfrom nltk.chunk import ChunkScore# 1 ref: https://linguistics.stackexchange.com/questions/28482/why-are-three-tags-necessary-for-the-iob-format-w.

import nltkfrom nltk.corpus import treebank# Ubiquitous Ambiguitygroucho_grammar = nltk.CFG.fromstring("""S -> NP VPPP -> P NPNP -> Det N | Det N PP | 'I'VP -> V NP | VP PPDet -> 'an' | 'my'N -> 'elephant' | 'pajamas'V -> '.

import nltkfrom nltk import load_parserfrom nltk.sem import chat80# 10.1 Querying a Databasenltk.data.show_cfg('grammars/book_grammars/sql0.fcfg')cp = load_parser('grammars/book_grammars/sql0.fcfg', trace=3)query = 'What cities are located in China.

from __future__ import divisionimport nltk, re, pprintfrom nltk.corpus import gutenberg, nps_chat, brownfrom urllib.request import urlopenfrom bs4 import BeautifulSoup# access electronic booksurl = "http://www.gutenberg.org/files/2358/2358.txt"r.

from __future__ import divisionimport nltkfrom nltk.corpus import gutenberg, brown, state_union, swadesh, names, cmudict, udhrfrom nltk.corpus import wordnet as wn# 1phrase = ["I", "like", 'noodles', "."]print(phrase+phrase)print(phrase*3)print(.

import nltkfrom nltk.corpus import conll2000, conll2002import re# Information Extractionlocs = [('Omnicom', 'IN', 'New York'), ('DDB Needham', 'IN', 'New York'), ('Kaplan Thaler Group', 'IN', 'New York'), ('BBDO South', 'IN',.