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。

Ask HN: A tool for writing English that checks “popularity” of used sentences?

126 点作者 twa927超过 8 年前
As a non-native English speaker I find that the best way to check grammar is to google whole parts of sentences (in apostrophes - exact match). It&#x27;s because there are multiple exceptions to language rules and some wording just can feel &quot;not right&quot; despite being correct.<p>Is there a tool that does something like this automatically?<p>I thought about writing such tool by myself, but it seems there are no good-quality, free search engine APIs that allow many calls. Or, maybe there are some open APIs to book dumps or something similar?

22 条评论

IanCal超过 8 年前
You might like to check out writeful: <a href="http:&#x2F;&#x2F;writefullapp.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;writefullapp.com&#x2F;</a>
评论 #12758552 未加载
评论 #12773102 未加载
antaviana超过 8 年前
AFAIK, an ex-Googler had that very same itch and he founded <a href="http:&#x2F;&#x2F;www.linguee.com" rel="nofollow">http:&#x2F;&#x2F;www.linguee.com</a> to try to solve it.
评论 #12757044 未加载
barryhunter超过 8 年前
There are quite a few Ngram datasets available <a href="https:&#x2F;&#x2F;www.google.com&#x2F;search?q=download+n-gram+dataset" rel="nofollow">https:&#x2F;&#x2F;www.google.com&#x2F;search?q=download+n-gram+dataset</a><p>... these are almost certainly used in many spelling and grammar checkers. (To help with where the same spelled word is used in different context)<p><a href="http:&#x2F;&#x2F;www.aclweb.org&#x2F;anthology&#x2F;W12-0304" rel="nofollow">http:&#x2F;&#x2F;www.aclweb.org&#x2F;anthology&#x2F;W12-0304</a>
评论 #12753964 未加载
评论 #12753988 未加载
aytekin超过 8 年前
I wonder if there is a tool like this:<p>1. You enter a sentence<p>2. It gives out 5 different ways to say the exact same thing.<p>Such a tool not only would help ESL people but also it would help native speakers find more relaxed or formal versions of a sentence.
评论 #12753985 未加载
评论 #12753749 未加载
评论 #12759420 未加载
infinitone超过 8 年前
Check out <a href="http:&#x2F;&#x2F;foxtype.com" rel="nofollow">http:&#x2F;&#x2F;foxtype.com</a> - does some of that but more grammar-like heuristics such as conciseness, complexity.<p>On a side note, I&#x27;m part of a team working on <a href="http:&#x2F;&#x2F;emailfox.co" rel="nofollow">http:&#x2F;&#x2F;emailfox.co</a> which will provide &#x27;Smart Sentences&#x27; for you when composing an email, based on a recipient. Allowing you to write personal, relevant emails faster.
评论 #12754390 未加载
评论 #12754216 未加载
rtrsqrrl超过 8 年前
Try <a href="http:&#x2F;&#x2F;www.netspeak.org&#x2F;?locale=en" rel="nofollow">http:&#x2F;&#x2F;www.netspeak.org&#x2F;?locale=en</a> it seems to do some of the things you asked. It is implemented on top of n-gram corpora.
评论 #12754089 未加载
Xeoncross超过 8 年前
You could probably use some of the Ngrams datasets to figure this out. Parse some books from <a href="https:&#x2F;&#x2F;www.gutenberg.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.gutenberg.org&#x2F;</a> or use the google ngrams corpus. Pay attention to the year(s) which you wish to model english from - grammar and form keep changing!
rebelde超过 8 年前
I have been thinking of doing something like this (using Ngrams for grammar check for non-natives) for a while. I would be happy to fund development if you or somebody else are interested in working on it.
franciscop超过 8 年前
From XKCD themselves, an editor that only allows for common words: <a href="https:&#x2F;&#x2F;xkcd.com&#x2F;simplewriter&#x2F;" rel="nofollow">https:&#x2F;&#x2F;xkcd.com&#x2F;simplewriter&#x2F;</a>
0xdeadbeefbabe超过 8 年前
www.grammarly.com (haven&#x27;t tried it though) In the demo they showed it turning a sentence into a more colloquial sentence.<p>I&#x27;m a native English speaker, and I&#x27;d like to know appropriate punctuation for a given combination of words. I&#x27;d like to search through a list.
评论 #12755640 未加载
ChicagoBoy11超过 8 年前
When I&#x27;m conflicted about different phrasings of things (for instance, if there is a hyphen or there isn&#x27;t on when writing compound words), I usually just use a google search and go with whatever result has the most number of hits. That could be a suitable enough proxy for your use-case, and perhaps you could just use the google search service as an API...<p>Of course, the RIGHT way to do this would be to use the n-gram datasets that people here have suggested :-)
mrtimuk超过 8 年前
In FAQ: &quot;Why does Google Books only provide feedback on 5 tokens or less?&quot;<p>You mean &quot;..feedback only for 5 tokens or FEWER?&quot; Use your app! ;) &#x2F;&#x2F;runs away
camelite超过 8 年前
Some thing like this: <a href="http:&#x2F;&#x2F;corpus.byu.edu&#x2F;bnc&#x2F;" rel="nofollow">http:&#x2F;&#x2F;corpus.byu.edu&#x2F;bnc&#x2F;</a> ?
hendler超过 8 年前
To improve the qualitative aspects of writing, in this case for job listings primarily, check out <a href="https:&#x2F;&#x2F;textio.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;textio.com&#x2F;</a>. There&#x27;s no API, but I think it will help you think about what &quot;popular&quot; language means.
nl超过 8 年前
What you want is a language model. This will give you the probability on a word by word basis.<p>Something like [1] is pretty much state-of-the-art. It&#x27;s worth noting that the kind of writing you are doing change the probability significantly. [2] shows this quite well.<p>[1] <a href="https:&#x2F;&#x2F;colinmorris.github.io&#x2F;lm-sentences&#x2F;#&#x2F;billion_words" rel="nofollow">https:&#x2F;&#x2F;colinmorris.github.io&#x2F;lm-sentences&#x2F;#&#x2F;billion_words</a><p>[2] <a href="https:&#x2F;&#x2F;colinmorris.github.io&#x2F;lm-sentences&#x2F;#&#x2F;brown_romance" rel="nofollow">https:&#x2F;&#x2F;colinmorris.github.io&#x2F;lm-sentences&#x2F;#&#x2F;brown_romance</a>
adrianratnapala超过 8 年前
Bah, if you have good reason to be confident that your sentence is correct even if English speakers might feel it is wrong, then I say you should just write it anyway.<p>I like to read such things because it makes me think about what is being said and how the language works. If we always use &quot;popoular&quot; patterns then our writing becomes cliched and boring and people&#x27;s eyes will glide right over it.
评论 #12759114 未加载
KayL超过 8 年前
If you can read Chinese, there&#x27;s interesting tool:<p><a href="http:&#x2F;&#x2F;www.pigai.org&#x2F;guest2016.html" rel="nofollow">http:&#x2F;&#x2F;www.pigai.org&#x2F;guest2016.html</a><p>It extracted common phrase from the sentences with explanations &amp; suggestions &amp; count usages from corpus.
ecesena超过 8 年前
Never found it, but if you build it count me in as a user. Same issue, same solution.
plusepsilon超过 8 年前
Thanks for the mention above (foxtype.com).<p>We&#x27;re currently building an online editor checks
评论 #12754692 未加载
hyperpallium超过 8 年前
\incidental Use quotes (&quot;) for exact match, not apostrophes (&#x27;).
0b01超过 8 年前
<a href="https:&#x2F;&#x2F;github.com&#x2F;rickyhan&#x2F;bodine" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;rickyhan&#x2F;bodine</a><p>This is a tiny tool I wrote a long time ago. There&#x27;s also writefullapp.com which is closed source.
kamillarott超过 8 年前
I can suggest <a href="http:&#x2F;&#x2F;samedaypapers.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;samedaypapers.com&#x2F;</a>. It always helps me)))