0%

AAAI2020 预讲会翻译对话与文本生成、文本分析与内容挖掘两个Session比较有意思的论文。

  • Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation [PDF][Slide]

  • Modeling Fluency and Faithfulness for Diverse Neural Machine Translation [PDF][Slide]

  • Task-Oriented Dialog Systems that Consider Multiple Appropriate Response under the Same Context [PDF][Slide]

  • Neural Machine Translation with Joint Representation [Slide]

  • Multi-Scale Self-Attention for Text Classification [PDF][Slide]

  • Intergrating Relation Constraints with Neural Relation Extractors [PDF][Slide]

  • Cross-Lingual Natural Language Generation via Pre-Training [PDF]

批量杀死包含关键字“keyword1”但不包含“keyword2”的进程。

1
ps -ef|grep keyword1|grep -v keyword2|cut -c 9-15|xargs kill -9
  • “ps -ef” ——查看所有进程
  • “grep keyword1” ——列出所有含有关键字”keyword1”的进程
  • “grep -v keyword2” ——在列出的进程中去除含有关键字”keyword2”的进程
  • “cut -c 9-15″ ——截取输入行的第9个字符到第15个字符,而这正好是进程号PID
  • “xargs kill -9″ ——xargs 命令是用来把前面命令的输出结果(PID)作为”kill -9″命令的参数,并执行该命令。”kill -9″会强行杀掉指定进程。

转载自:知乎专栏 NLP日知录 https://zhuanlan.zhihu.com/p/93765082

作者:刘知远

背景说明:临近ACL 2020投稿截止时间,跟同学密集讨论,争论哪些研究想法适合投到ACL有机会命中。从自己十多年研究经历来看,如何判断一个研究想法好不好,以及这些研究想法从哪里来,对于初学者而言的确是个难题。所以,简单攒了这篇小短文,分享一些经验和想法,希望对刚进入NLP领域的新同学有用。多有舛误请指正。

阅读全文 »

任务简介

A keyphrase or keyword is a piece of short, summative content that expresses the main semantic meaning of a longer text. The typical use of a keyphrase or keyword is in scientific publications to provide the core information of a paper.

阅读全文 »