search

microsoft / ProphetNet

A research project for natural language generation, containing the official implementations by MSRA NLC team.
MIT License
686 stars 109 forks source link

It seems that the core code of CRITIC, particularly the part involving Google API search, is not implemented #67

Closed zyg18181818 closed 12 months ago

WWWonderer commented 12 months ago

+1

Hi, I'm also mostly interested in how you used google API search to retrieve relevant results to the question. Please share the code it will really help! Thank you!

ZubinGou commented 12 months ago

Hi, thanks for your interest! To simplify, using text from the top result returned by the Google Search API is enough. Furthermore, due to budget constraints and the need for stable, reproducible results, we developed a Google and web page crawler with cache for our experiments (storing about 9GB of Google results from January-April 2023). This part of the code is complex, and we don't recommend trying it at the moment. We may consider organizing and open-sourcing the crawler separately in the future. Stay tuned for updates, and we appreciate your understanding!

zyg18181818 commented 11 months ago

Thank you very much for taking the time to reply. I will continue to follow your work and look forward to future communication.  

周艺耕 @.***

 

------------------ 原始邮件 ------------------ 发件人: "Zhibin @.>; 发送时间: 2023年10月9日(星期一) 晚上11:30 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [microsoft/ProphetNet] It seems that the core code of CRITIC, particularly the part involving Google API search, is not implemented (Issue #67)

Hi, thanks for your interest! To simplify, using text from the top result returned by the Google Search API is enough. Furthermore, due to budget constraints and the need for stable, reproducible results, we developed a Google and web page crawler with cache for our experiments (storing about 9GB of Google results from January-April 2023). This part of the code is complex, and we don't recommend trying it at the moment. We may consider organizing and open-sourcing the crawler separately in the future. Stay tuned for updates, and we appreciate your understanding!

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

WWWonderer commented 11 months ago

All right thank you for your reply! Looking forward to the open-source of the crawler!