Google Open-Sources SyntaxNet Natural-Language Understanding Library, Parsey McParseface Training Model 56
Google announced on Thursday that it is open sourcing its new language parsing model called SyntaxNet. It's a piece of natural-language understanding software, Google says, that you can use automatically parse sentences, as part of its TensorFlow open source machine learning library. The company also announced that it is releasing something called Parsey McParseface (Google has a sense of humor), which is a pre-trained model for parsing English-language text. Nate Swanner of The Next Web, attempts to explain it: Combining machine learning and search techniques, Parsey McParseface is 94 percent accurate, according to Google. It also leans on SyntaxNet's neural-network framework for analyzing the linguistic structure of a sentence or statement, which parses the functional role of each word in a sentence. If you're confused, here's the short version: Parsey and SyntaxNet are basically like five year old humans who are learning the nuances of language. In Google's simple example above, 'saw' is the root word (verb) for the sentence, while 'Alice' and 'Bob' are subjects (nouns). Parsey's scope can get a bit broader, too.
Re: (Score:1)
Knowledge workers process natural language inquiries and recall from the 0.01% of human knowledge they have managed to memorize the relevant details to solve the problem, identify where to look for more information, and/or refer the inquiring individual to the correct resource they need to solve the problem themselves.
A computer capable of parsing natural language inquiries can construct an appropriate query of all publicly accessible digitized human knowledge and analyze the contents of that knowledge to i
Fail (Score:1)
It's a piece of natural-language understanding software, Google says, that you can use automatically parse sentences, as part of its TensorFlow open source machine learning library.
YOU CAN USE AUTOMATICALLY PARSE SENTENCES
SubjectsSuck (Score:2)
So, can Parsey McParseface make sense of what manishs posts? Because I generally can't. I assume that the example sentence from the summary probably came from the article, but for some reason the "editor" didn't think to read his summary to make sure that it actually made sense out of context.
Re: (Score:2)
The claim was parse, not make sense of. And it's not clear that it can parse all sentences. Some sentences can't be unambiguously parsed even when you know the context and each included word.
Re: (Score:3)
It all read just fine to me. The only mistake I noticed was that
should have been
since it is the software doing the understanding, not the language. The quote itself is clear and concise. If you didn't understand it that probably just means you lack the technical vocabulary to even make use of the tool.
google tries to be humorous (Score:1)
"Parsey McParseface (Google has a sense of humor)"
more like dour corp peons at google tries hard, very hard, to appear humorous.
even tay had better humor
Re: (Score:2)
that is precisely why it is not funny. google peons are just parroting something funny to try to be funny.
Prase this, McParseface (Score:2)
James while John had had had had had had had had had had had a better effect on the teacher.
Re:Prase this, McParseface (Score:5, Interesting)
...and while McParseface is at it, he can chew on:
"Wouldn't the sentence 'I want to put a hyphen between the words Fish and And and And and Chips in my Fish-And-Chips sign' have been clearer if quotation marks had been placed before Fish, and between Fish and and, and and and And, and And and and, and and and And, and And and and, and and and Chips, as well as after Chips?"
Re: (Score:2)
It should be easy enough to set it up to parse that sort of thing as "blah blah blah" and leave it at that. ;)
I'd also want anything more than triple negated to equal "blah blah blah."
Buffalo buffalo buffalo (Score:2)
Bison from Buffalo, New York, are known to bully other Buffalo bison, who in turn bully (buffalo) other New York bison. In other words:
Buffalo buffalo buffalo buffalo buffalo buffalo buffalo.
Re: (Score:2)
Re: (Score:2)
That's quite a stutter. :)
WELCOME OVERLORDS! HAW HAW HAW!! (Score:2)
The company also announced that it is releasing something called Parsey McParseface (Google has a sense of humor)..
If by 'sense of humor' you mean 'a repeat of something that was humorous a while ago under a different context'.
Re: (Score:2)
You parsed it wrong. "Sense of humor" here does not indicate that the words are funny; it indicates that the words are goofy or foolish, and that Google was willing to let a thing be named that way.
I recommend checking a dictionary. There are about a dozen meanings of the word humor, and probably half of them cover this particular usage. One advantage of a computer parser is that it is unlikely to reject a valid statement merely because it didn't consider all of the known patterns.
Re: (Score:2)
'a repeat of something that was humorous a while ago under a different context'
like your sig?
I'm here all night, try the veal.
Time flies like an arrow. (Score:4, Interesting)
Fruit flies like a banana.
Re: (Score:2)
What's a "time fly"?
Re: (Score:2)
What's a "time fly"?
My guess is it's what happens when you cross Dr. Who with The Fly.
Permutaton of all parsable sentences? (Score:2)
A concise version of the Library of Babel [wikipedia.org] expressing every idea if a language?
Re: (Score:2)
The set of all parsable sentences is trivially unbounded, at least in English.
A sentence can go on, {and on,}* and on.
Re: (Score:2)
While all parsable sentences is unbounded, the ones limted to human understanding are.
Re: (Score:2)
I can't see why they would be. More rigorously, I don't think you can establish a bound on the length of sentences that are humanly understandable. The sentences generated by my little example are all humanly understandable, for example, even though they're of unbounded length.
Shite (Score:2)
Not really, because Xy McXface is not funny for any value of X.
Re: (Score:1)
^ Grumpy McGrumpface
Rule-based still easily best (Score:3)
94% syntax is definitely good, for a machine learning parser. Now if you were to come to the land of rule-based parsers, 94% is the norm.
Google loves machine learning, and it's easy to see why. That's how they made their whole stack. They have the huge amounts of data to train on, and the hardware to do so. It's so seductive to just throw a mathematical model at huge amounts of data and let it run for a few weeks.
Rule-based systems don't need any data to work with - they just need a computational linguist to spend a year writing down the few thousand rules. But the end result is vastly better, fully debuggable, easily updatable, understandable, and domain independent. That last bit is really important. A system trained for legalese won't work on newspapers, but a rule-based system usually works equally well for all domains.
In 2006, VISL [visl.sdu.dk] had a rule-based parser doing 96% syntax for Spanish (PDF) [visl.sdu.dk] - our other parsers are also in that range, and naturally improved since then. Google is hopelessly behind the state of the art.
Re: (Score:2)
You kinda alluded to the reason yourself...
> Rule-based systems don't need any data to work with - they just need a computational linguist to spend a year writing down the few thousand rules
which seams much more expensive than
> ... just throw a mathematical model at huge amounts of data and let it run for a few weeks.
but can now yield nearly equal results. "Machine Learning" sounds cooler than a bunch of if statements too
Re: (Score:3)
which seams much more expensive than
It'd seem that way, but it's really not if you factor in the whole chain.
Machine learning needs high quality annotated treebanks to train from. Creating those treebanks takes many many years. It is newsworthy when a new treebank of a mere 50k words is published. Add to that the fact that each treebank likely uses different annotations, and you need to adjust your machine learner for that, or add a filter. Plus each treebank is for a specific domain, so your finished parser is domain-specific. If you want to
Re: (Score:2)
Who said they're giving away their best stuff?
The nature of machine learning does. All they're giving away is an algorithm and a system trained using that algorithm. Linguistic machine learning is a field where even a 0.5% improvement takes years to get and is worth a paper. So even if they aren't giving away their top algorithm, their best one can't be much better.
Re: (Score:2)
I have not read the original article, so take my comments with some grains of salt.
But speaking as one who once wrote a syntactic grammar for a parser of English (still in use by a large manufacturer 30 years later, albeit in modified form), the problem with rule-based grammars that lack any statistical weights is that they come up with an unbelievably large number of parses for many real-world sentences. The problem is then to find which of those parses is the correct one, and that's what statistical weig
Re: (Score:2)
...the problem with rule-based grammars that lack any statistical weights is that they come up with an unbelievably large number of parses for many real-world sentences.
Generative grammars suffer from that problem and scales very poorly, and may indeed be impractical to use for real world text. Our constraint grammars [wikipedia.org] and finite-state analysers [github.io] do not have that problem. With CG, we inject all the possible ambiguity into the very first analysis phase, then use contextual constraints to whittle them down, where context is the whole sentence or even multiple sentences. This means performance scales linearly with number of rules.
So the 96% accuracy claim is suspect, not to mention that a comparison of the Google system is already difficult because Spanish =/= English. (Spanish has more morphology on verbs, it's pro-drop, it has relatively free word order compared to English,...)
The paper is for Spanish, because that's what I
Lawyers For Horsey McHorseface Will Be In Touch (Score:1)
A two-year-old gelding destined to race in Australia has been saddled with the name Horsey McHorseface. (pun intended by editors)
http://www.bbc.com/news/world-... [bbc.com]