Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

An Upgrade to SyntaxNet, New Models and a Parsing Competition

research.googleblog.com

Post reply on HN
Print view View original

71–80 of 93 posts

Re: An Upgrade to SyntaxNet, New Models and a Parsing Competition

#71

Post by squeaky-clean »

detaro wrote: post #47
squeaky-clean wrote: post #16

Earlier quoted context omitted.

I've been slowly working on my own simple home "Alexa" using mostly CMUSphinx for the voice detection. Honestly my most successful methods involved the least amount of complex NLP. Just simply treating the sentence as a bag of words and looking for "on" or "off" or "change" (and their synonyms) and the presence of known smart objects works extremely well. I could say "Hey Marvin, turn on the lights and TV", or "Hey M…

This was recently mentioned on HN, but I haven't really looked into it (apparently requires training your own models, but provides prepared scripts to do that for some common datasets): https://github.com/mozilla/DeepSpeech

Must have slipped past me last time it was posted on HN. Thanks for sharing! I'm going to add this to my list of things to try next time I'm inspired to work on this project again.

Re: An Upgrade to SyntaxNet, New Models and a Parsing Competition

#72

Post by jtraffic »

taliesinb wrote: post #51
jtraffic wrote: post #46

Earlier quoted context omitted.

Two times in my life, I've gotten deeply excited about Mathematica. The first time I wanted to use it for economics homework as an undergraduate. (Don't worry, I did it on paper first.) The second time, I wanted to use it for machine learning, especially NLP. Mainly the knowledge base Mathematica hooks into is what drew me. The problem in the end is that the customizability of Mathematica ends right where things get…

> If you want to show people cool little examples, Mathematica is clean and fast, but you can't build anything serious with it. Mathematica, which is a serious project, is largely written in Mathematica. Wolfram|Alpha, another large project, is built in Mathematica. Outside the company, https://emeraldcloudlab.com/ for example has built their platform on Mathematica. > And by "serious", I guess I mean something with…

Good points. I will admit that what I said: "you can't build anything serious with it" is too extreme. I'm not sure how to count Mathematica and Wolfram|Alpha, though. Still, Emerald Cloud Lab clearly gets credit.

Re: An Upgrade to SyntaxNet, New Models and a Parsing Competition

#73

Post by dang »

liviosoares wrote: post #69
dang wrote: post #58

We changed the title from "Google open-sources Tensorflow-based framework for NLP", which appears misleading, given that it happened last May: https://news.ycombinator.com/item?id=11686029 . On HN the idea is to rewrite titles only to make them less misleading (or less baity). Please see https://news.ycombinator.com/newsguidelines.html .

dang, sorry if this seemed misleading. In my humble opinion, the blog title does not do full justice to the new release, primarily since it carries a new framework within SyntaxNet: https://github.com/tensorflow/models/blob/master/syntaxnet/g... This new DRAGNN framework is what I thought the folks here would want to know. Perhaps I should have linked to the github page, rather than the blog announcement.

Ah, I see. Probably a post pointing to that framework would have been a better idea. It never fails to surprise me, but discussion tends to be directed almost entirely by what's in a submission title.

For the same reason, it probably doesn't make sense to change the current thread to point to that Github page now, since that would orphan the existing discussion.

Re: An Upgrade to SyntaxNet, New Models and a Parsing Competition

#74

Post by steren »

aseipp wrote: post #33
jorgemf wrote: post #19

Earlier quoted context omitted.

It is not a good idea to compile TensorFlow by your own unless you really need it (for example for TensorFlow serving). Python packages are the way to go.

This is a bit unfortunate, in a real sense. I mean, I already build enough software, so I'm not sad on missing out. But here's the thing: TensorFlow actually installed great on Windows and it took less than 10 minutes to get running, once I had Python3 installed, even with GPU support. Even worked awesome in VS Code, out of the box, with autocomplete in the python mode. Even a baby like me got started easily. But it'…

Hi, I am working on Bazel, the build tool used by Tensorflow.

Could you please share in more details the problems you encountered with Bazel?

If you have specific questions, I encourage you to post on StackOverflow with the bazel and tensorflow tags, both the Bazel and Tensorflow teams are monitoring and answering questions there.

Re: An Upgrade to SyntaxNet, New Models and a Parsing Competition

#75

Post by Nullabillity »

taliesinb wrote: post #51
jtraffic wrote: post #46

Earlier quoted context omitted.

Two times in my life, I've gotten deeply excited about Mathematica. The first time I wanted to use it for economics homework as an undergraduate. (Don't worry, I did it on paper first.) The second time, I wanted to use it for machine learning, especially NLP. Mainly the knowledge base Mathematica hooks into is what drew me. The problem in the end is that the customizability of Mathematica ends right where things get…

> If you want to show people cool little examples, Mathematica is clean and fast, but you can't build anything serious with it. Mathematica, which is a serious project, is largely written in Mathematica. Wolfram|Alpha, another large project, is built in Mathematica. Outside the company, https://emeraldcloudlab.com/ for example has built their platform on Mathematica. > And by "serious", I guess I mean something with…

> For research, a "thing you can do with Mathematica" is often what you want. But other than that you can put things you build in the cloud via APIFunctions (similar to AWS Lambda functions), or call out to them via wolframscript, or talk to kernels directly via MathLink or LibraryLink, or over sockets via ChannelListen.

For research, closed source should be a dealbreaker.

Re: An Upgrade to SyntaxNet, New Models and a Parsing Competition

#76

Post by seanmcdirmid »

Nullabillity wrote: post #75
taliesinb wrote: post #51

Earlier quoted context omitted.

> If you want to show people cool little examples, Mathematica is clean and fast, but you can't build anything serious with it. Mathematica, which is a serious project, is largely written in Mathematica. Wolfram|Alpha, another large project, is built in Mathematica. Outside the company, https://emeraldcloudlab.com/ for example has built their platform on Mathematica. > And by "serious", I guess I mean something with…

> For research, a "thing you can do with Mathematica" is often what you want. But other than that you can put things you build in the cloud via APIFunctions (similar to AWS Lambda functions), or call out to them via wolframscript, or talk to kernels directly via MathLink or LibraryLink, or over sockets via ChannelListen. For research, closed source should be a dealbreaker.

By "research" I suppose you were being overly specific to mean publicly funded research?

Re: An Upgrade to SyntaxNet, New Models and a Parsing Competition

#77

Post by coding123 »

I've been rummaging through the docs on DRAGONN but can't seem to find proper installation/run instructions. There is a Google Cloud installation, but I want to just run on my laptop for now against the pre-trained files. Can't seem to get started with DRAGONN.

Re: An Upgrade to SyntaxNet, New Models and a Parsing Competition

#78

Post by woodson »

squeaky-clean wrote: post #16
canada_dry wrote: post #6

Hoping this will quickly make into someone's home grown self-hosted version of Alexa. Alexa, turn the lights on in the kitchen. Alexa, turn on the kitchen light. Alexa, light up the kitchen. Should all accomplish the same task using this framework.

I've been slowly working on my own simple home "Alexa" using mostly CMUSphinx for the voice detection. Honestly my most successful methods involved the least amount of complex NLP. Just simply treating the sentence as a bag of words and looking for "on" or "off" or "change" (and their synonyms) and the presence of known smart objects works extremely well. I could say "Hey Marvin, turn on the lights and TV", or "Hey M…

Kaldi is not a point-and-click solution, it's a toolkit to develop your own speech recognition system. That said, it makes it incredibly easy if you know what you're doing, as it brings all the necessary tools and even provides some data to train your models (see the associated resources at http://openslr.org/). It's performance is state of the art.

Re: An Upgrade to SyntaxNet, New Models and a Parsing Competition

#79

Post by Houshalter »

minimaxir wrote: post #45
tlow wrote: post #43

For those of us who aren't developers but maybe more aptly called "hackers" (cause we hack stuff together even though we're operating out of our league, sometimes we get stuff to work). I am wondering, is there a even higher level guide to using Tensor Flow. I am currently growing Sweet Peas in my office in enclosed containers that automanage environment, nutrition and water. I have the capaability to log a lot of da…

The short answer is to skip TensorFlow entirely and use/learn Keras for a high-level overview; then you can learn top-down if you need to use/look at TF code directly. Another HN thread has good tutorials for simple uses of Tensorflow: https://news.ycombinator.com/item?id=13464496 However, NNs are optimal for text/image data as they can learn the features. If your data features are already known, you don't necessaril…

sklearn has this flowchart for what machine learning method to use: http://scikit-learn.org/stable/_static/ml_map.png

Re: An Upgrade to SyntaxNet, New Models and a Parsing Competition

#80

Post by minimaxir »

Houshalter wrote: post #79
minimaxir wrote: post #45

Earlier quoted context omitted.

The short answer is to skip TensorFlow entirely and use/learn Keras for a high-level overview; then you can learn top-down if you need to use/look at TF code directly. Another HN thread has good tutorials for simple uses of Tensorflow: https://news.ycombinator.com/item?id=13464496 However, NNs are optimal for text/image data as they can learn the features. If your data features are already known, you don't necessaril…

sklearn has this flowchart for what machine learning method to use: http://scikit-learn.org/stable/_static/ml_map.png

The flowchart predates NNs/GBTs which are Swiss-army knives, which is another reason why using either of them is sometimes considered cheating.
Post reply on HN