TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

SyntaxNet – An open-source framework for Natural Language Understanding systems

54 点作者 bluesilver07大约 8 年前

3 条评论

mxstbr大约 8 年前
Previous discussion for same article: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=11686029" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=11686029</a><p>Previous discussion after recent update announcement: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=13885685" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=13885685</a>
d0100大约 8 年前
&gt; Humans do a remarkable job of dealing with ambiguity, almost to the point where the problem is unnoticeable;<p>Isn&#x27;t this because we have knowledge of the world?<p>The sentence &quot;Alice drove down the street in her car&quot; won&#x27;t ever be parsed as &quot;the street is in the car&quot; by a human because we know that streets don&#x27;t go in cars.<p>Computers won&#x27;t ever solve this without having a larger knowledge base to compare the parsed sentences and remove the ridiculous outputs.
simongray大约 8 年前
&gt; Thursday, May 12, 2016