Show HN: An easy-to-use Text Analysis API – NLP and Machine Learning

153 点作者 parsabg超过 11 年前

30 条评论

gklitt超过 11 年前

Cool stuff! It's nice to see platforms like this which abstract out good algorithms, so that developers can worry about thinking of interesting applications. .Open source libs are even better, but pragmatically speaking, I think these types of platforms probably move faster and get better results.One major competitor (well known for anyone who's looked into this stuff) is Alchemy [1]. I tried a New York Times link [2] on Aylien and Alchemy, and Alchemy performed much better -- in fact, Aylien didn't even successfully find the article body. I'm sure you guys will be iterating on improving the algorithms, but just wanted to flag that as a potential turnoff for anyone comparing your website demo with Alchemy.Best of luck![1] <a href="http://www.alchemyapi.com/products/demo/" rel="nofollow">http://www.alchemyapi.com/products/demo/</a>[2] <a href="http://www.nytimes.com/2014/02/18/world/middleeast/bombings-in-syria-force-wave-of-civilians-to-flee.html?hp&_r=0" rel="nofollow">http://www.nytimes.com/2014/02/18/world/middleeast/bombings-...</a>

评论 #7257800 未加载

评论 #7260339 未加载

fnl超过 11 年前

Seen quite a few times (NLP web APIs), and my opinion is that this kind of stuff tends to not be scalable: to be useful, such web APIs have to be able to do entire articles in just a split fraction of a second. Although I am not sure (because of the HN storm the API is down), it does not seem this tool will live up to those expectations, either. In the end, my choice always has been to include/wrap an off-the-shelf tool in your own pipeline rather than relying on a external service that might be too slow for end-users and mass mining alike...

评论 #7262275 未加载

drakaal超过 11 年前

This is a much better Noun Phrase / Entity extractor.<a href="https://www.mashape.com/stremor/noun-entity-extraction-noun-phrase-part-of-speech-tagger-alpha" rel="nofollow">https://www.mashape.com/stremor/noun-entity-extraction-noun-...</a>We don't rely on CoreNLP, or NLTK, we have our own sentence disambiguation, and our own part of speech tools. So we are a lot faster.Our other api's let you piece together a lot of cool NLP projects with very little code.

mattmcknight超过 11 年前

These sorts of things are typically better offered as libraries, particularly as the training is usually specific to a corpus, or a particular context.It would be a nice to offer a library with a bootstrapped training set.

评论 #7258168 未加载

kenshiro_o超过 11 年前

Unfortunately the web site is still analyzing the example Techcrunch link (it's been 3 min already).Is something broken? Maybe you could cache some recurring analyses.

评论 #7257970 未加载

评论 #7257969 未加载

zvanness超过 11 年前

Hey guys! Congrats, NLP is a huge problem that needs as many minds working on it as possible.Just tried a few links:<a href="http://arstechnica.com/security/2014/02/dear-asus-router-user-youve-been-pwned-thanks-to-easily-exploited-flaw/" rel="nofollow">http://arstechnica.com/security/2014/02/dear-asus-router-use...</a><a href="http://blog.algore.com/2011/07/the_great_lakes_are_in_danger.html" rel="nofollow">http://blog.algore.com/2011/07/the_great_lakes_are_in_danger...</a>Am I missing something here? It seems like it's just parsing text, i'm not seeing any context(keywords, categories, summaries)edit: It's giving fantastic results when pasting the raw text! :)Are you guys using DBpedia? It's giving very similar results to a system I was working on in the past: <a href="http://www.zachvanness.com/nanobird_relevancy_engine.pdf" rel="nofollow">http://www.zachvanness.com/nanobird_relevancy_engine.pdf</a>

评论 #7257789 未加载

blueblob超过 11 年前

What do you use for the extraction of entities (if you don't mind saying)? I entered "The Cat in the Hat" is a good book. It didn't recognize any entities. Are you using an ontology for named entity resolution, or just extracting NPs?

评论 #7258740 未加载

analytically超过 11 年前

Another player in this space, from Oxford, UK: <a href="http://apidemo.theysay.io/" rel="nofollow">http://apidemo.theysay.io/</a>

imperio59超过 11 年前

It does really poorly analyzing a Wiktionary entry like <a href="http://en.wiktionary.org/wiki/run" rel="nofollow">http://en.wiktionary.org/wiki/run</a> or with a Wikipedia article like <a href="http://en.wikipedia.org/wiki/Big_O_notation" rel="nofollow">http://en.wikipedia.org/wiki/Big_O_notation</a>

bane超过 11 年前

Playing around with it and seemed to have killed it by pasting the text from this WP article (<a href="http://pastebin.com/AtCU7E8H" rel="nofollow">http://pastebin.com/AtCU7E8H</a>) in and hitting analyze. It's been spinning for a while.edit I see from another response that the server room is on meltdown, I'll wait for a bit.

crypto5超过 11 年前

Maybe somebody will find useful and relevant my pet project: <a href="https://github.com/crypto5/wikivector" rel="nofollow">https://github.com/crypto5/wikivector</a> . It uses machine learning and wikipedia data as training set, supports 10 languages, and completely open source.

syllogism超过 11 年前

Do you publish accuracy figures? Any information about what domains your training data is from?

评论 #7258020 未加载

polskibus超过 11 年前

There's more and more of text analysis APIs, would you mind comparing your feature set to something like Textrazor (<a href="http://www.textrazor.com" rel="nofollow">http://www.textrazor.com</a>) or Open Calais?What is special about your project ?

评论 #7259278 未加载

skiplecariboo超过 11 年前

Super nice !This is a very interesting area... Good to see something new apart from Alchemy and opencalais !

评论 #7257843 未加载

cliveowen超过 11 年前

"There was a time when men could roam free on earth, free from concrete and tarmac. Now it's all gone to shit."Classification: arts, culture and entertainment - architecture .(WTF?)Polarity: positive. (Nope)Polarity confidence: 0.9994709276706056. (Well...)Looks pretty rough to me.

评论 #7258381 未加载

评论 #7257773 未加载

评论 #7258416 未加载

ksk超过 11 年前

A bunch of TA libraries (Stemmers, Wordbreakers, etc) ship "free" with Windows that support a ton of different languages. I wish MS would open up the API a bit more.

elwell超过 11 年前

Clearly broken. Say's news.ycombinator.com sentiment is "Positive". All jokes aside, really cool; love the accessibility of the demo.

cglace超过 11 年前

I posted a couple of paragraphs from a financial blog and the tool interpreted SEC to mean Southeastern Conference.

评论 #7258160 未加载

moron4hire超过 11 年前

Should I have not tried it with a 3000 word essay I wrote? It has been beachballing for the last 5 minutes or so.

评论 #7257886 未加载

adventured超过 11 年前

How is this superior to Alchemy?<a href="http://www.alchemyapi.com/" rel="nofollow">http://www.alchemyapi.com/</a>

评论 #7257828 未加载

mrg3_2013超过 11 年前

I tried bbc.com and nothing shows up. Is it supposed to work on top level links and summarize ?

评论 #7258343 未加载

Houshalter超过 11 年前

I can't get it to work, can someone tell me what it's supposed to do?

parsabg超过 11 年前

thanks for the feedback folks. FWIW, here's the documentation (/ NLP crash course!): <a href="http://aylien.com/text-api-doc" rel="nofollow">http://aylien.com/text-api-doc</a>

iamwithnail超过 11 年前

Annnnnnd that's my thesis sorted. Part of it anyway.

afshinmeh超过 11 年前

One of stunning stuffs that I've seen. Good job.

lukasm超过 11 年前

HN - the ultimate DDOS machine

评论 #7257983 未加载

评论 #7258203 未加载

评论 #7257875 未加载

jhbellz超过 11 年前

pretty cool - what languages does your API support?

评论 #7257846 未加载

mm0超过 11 年前

sell it to a bank $$$

jackson1988超过 11 年前

This is incredible!

hamed_r超过 11 年前

Interesting!