地址：https://2021.naacl.org/program/accepted/

Paper List

会议接受论文通过爬虫提取到下面的excel中
共计：528篇
NAACL2021 Paper List.xlsx
NAACL2021 Paper List.xlsx

快速检索小工具

使用.py文件快速检索NAACL

  1. import pandas as pd
  2. import requests
  3. from lxml import etree
  4. def get_pdf(key):
  5.     url_format = "https://arxiv.org/search/?query={}&searchtype=all&abstracts=show&order=-announced_date_first&size=50"
  6.     rep = requests.get(url_format.format(key))
  7.     body = etree.HTML(rep.content)
  8.     ols = body.xpath(r'//*[@id="main-container"]/div[2]/p[1]/text()')
  9.     if ols:
  10.         ols = "Sorry, your query for all: {} produced no results.".format(r"Knowledge Guided Metric Learning for Few-Shot Text Classification get")
  11.         print(ols)
  12.     else:
  13.         ols = body.xpath(r'//*[@id="main-container"]/div[2]/ol/li')
  14.         for ol in ols:
  15.             print("[PDF]:",ol.xpath(r'./p[1]/text()')[0].replace("\n","").replace(" ",""),ol.xpath(r'./div/p/span/a[1]/@href')[0])
  17. # 查询关键词列表函数
  18. def Search_domain_print(key_list,df,withPdf=False):
  19.     keys = set([key.lower() for key in key_list])
  20.     for key in keys:
  21.         count = 0
  22.         for i in df["title"].values.tolist():
  23.             if key in i.lower():
  24.                 count = count + 1
  25.                 print("[{}]-[{}]:{}".format(key,count,i))
  26.                 if withPdf:
  27.                     get_pdf(i)
  28.                 print()
  30. if __name__ == '__main__':
  31.     excel = pd.read_excel("data/NAACL2021 Paper List.xlsx")
  32.     key_list = ["Text Classification",
  33.     #             "Sentiment Analysis","Knowledge Graph",
  34.                ]     
  35.     # withPdf设置为True可以直接检索并获取pdf，但速度会很慢。
  36.     # 也可以使用单步函数get_pdf("标题")直接查询要的文章
  37.     excel = pd.read_excel('data/NAACL2021 Paper List.xlsx')
  38.     Search_domain_print(key_list,excel,withPdf=False)

效果：
image.png
获得pdf效果：
image.png

Attention：

Knowledge Guided Metric Learning for Few-Shot Text Classification
少样本学习、文本分类、知识导向

DART: Open-Domain Structured Data Record to Text Generation
开放域数据、结构化数据、文本生成

Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
少样本学习、三重网络、数据增强、文本分类

News Headline Grouping As A Challenging NLU Task
新闻标题、NLU