技术控

    今日:61| 主题:49101
收藏本版 (1)
最新软件应用技术尽在掌握

[其他] Answering Featured Snippets Timely, Using Sentence Compression on News

[复制链接]
银枪小伪娘 发表于 前天 06:07
55 2

立即注册CoLaBug.com会员,免费获得投稿人的专业资料,享用更多功能,玩转个人品牌!

您需要 登录 才可以下载或查看,没有帐号?立即注册

x
Another place that would benefit from machine learning would be generating featured snippets that answer questions people might ask at Google, and it appears that they thought it might be useful there, too. A Wired Magazine article from Monday describes how those featured snippets might be generated:
      Google’s Hand-Fed AI Now Gives Answers, Not Just Search Results  
  At the heart of this approach is the crawling of a data store of news articles and other sources, with the help of a “massive team of PhD linguists it calls Pygmalion”, and the use of algorithms that are referred to as “sentence compression” algorithms that might generate answers to questions from sources such as that news source.
  Curious, I went in search of patents from Google that used “sentence compression” algorithms, and I found one:
          Methods and apparatus related to sentence compression   
    Inventors: Ekaterina Filippova and Yasemin Altun
    Assigned to: Google
    US Patent 9,336,186
    Granted: May 10, 2016
    Filed: October 10, 2013
    Abstract
  Methods and apparatus related to sentence compression. Some implementations are generally directed toward generating a corpus of extractive compressions and associated sentences based on a set of headline, sentence pairs from documents. Some implementations are generally directed toward utilizing a corpus of sentences and associated sentence compressions in training a supervised compression system. Some implementations are generally directed toward determining a compression of a sentence based on edge weights for edges of the sentence that are determined based on weights of features associated with the edges.
  The patent doesn’t mention featured snippets, but it does mention paraphrasing sentences in a data store of titles and sentences from a news source:
    The documents from which the set of headline, sentence pairs is determined may be news story documents. In some of those implementations, for each of the headline, sentence pairs the sentence is a first sentence of the respective document.
    Determining the set of headline, sentence pairs of the set may include: determining non-conforming headline, sentence pairs from a larger set of headline, sentence pairs; and omitting the non-conforming headline, sentence pairs from the set of headline, sentence pairs. Determining non-conforming headline, sentence pairs may include determining the non-conforming sentence pairs as those that satisfy one or more of the following conditions: the headline is less than a headline threshold number of terms, the sentence is less than a sentence threshold number of terms, the headline does not include a verb, and the headline includes one or more of a noun, verb, adjective, and adverb whose lemma does not appear in the sentence.
    I had hoped to find more that discussed how this algorithm might be used in the generation of featured snippets, but it didn’t provide many details on that aspect of how these algorithms might be used. It does appear to be based on natural language processing. and I went looking at Google whitepapers to see if I could find more. I found a paper that looked related. On a Research at Google page for the paper    Overcoming the Lack of Parallel Data in Sentence Compressionthey tell us is “A subset of the described data (10,000 sentence & extracted headlines pairs, with source URL and annotations) is available for    download.”  
  That data for download includes sentences from news articles that have been tagged as different parts of speech. It looks like a lot of work, but it appears to be done in a way that does take advantage of automate processes that can keep such information up to date.
  This appears to be how terms such as “sentence compression” become relevant to what SEOs do.
友荐云推荐




上一篇:A short guide to learn neural networks, and get famous and rich then.
下一篇:Build A Media Library With React, Redux, and Redux-saga – Part 2
酷辣虫提示酷辣虫禁止发表任何与中华人民共和国法律有抵触的内容!所有内容由用户发布,并不代表酷辣虫的观点,酷辣虫无法对用户发布内容真实性提供任何的保证,请自行验证并承担风险与后果。如您有版权、违规等问题,请通过"联系我们"或"违规举报"告知我们处理。

董堰平 发表于 昨天 00:04
一觉醒来,天都黑了。
回复 支持 反对

使用道具 举报

何玉红 发表于 昨天 02:24
好好顶贴,天天向上!
回复 支持 反对

使用道具 举报

*滑动验证:
您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

我要投稿

推荐阅读

扫码访问 @iTTTTT瑞翔 的微博
回页顶回复上一篇下一篇回列表手机版
手机版/CoLaBug.com ( 粤ICP备05003221号 | 文网文[2010]257号 )|网站地图 酷辣虫

© 2001-2016 Comsenz Inc. Design: Dean. DiscuzFans.

返回顶部 返回列表