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

81–90 of 93 posts

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

#81

Post by Houshalter »

minimaxir wrote: post #80
Houshalter wrote: post #79

Earlier quoted context omitted.

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.

NNs are much older than this chart. They aren't terribly good at problems like this because they tend to overfit more than other methods. They need lots of data to generalize well. They only really excel when the data has regular structure that can be exploited by weight sharing (like CNNs to images or RNNs to time series.)

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

#82

Post by rspeer »

jacquesm wrote: post #28
minimaxir wrote: post #24

Earlier quoted context omitted.

sudo pip install tensorflow works fine as of the recent v1.0, and works out of the box for CPU training. The annoying thing for GPU training is handling the cudNN dependency, which Google's guides are annoyingly lacking.

> The annoying thing for GPU training is handling the cudNN dependency, which Google's guides are annoyingly lacking. I've found a nice workaround for that one that does not require registration with nvidia so you can automate it: ML_REPO_PKG=nvidia-machine-learning-repo-ubuntu1404_4.0-2_amd64.deb wget http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1404/x86_64/${ML_REPO_PKG} -O /tmp/${ML_RE…

I'm assuming from the filename that that only works if you're on Ubuntu 14.04, right?

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

#83

Post by jacquesm »

rspeer wrote: post #82
jacquesm wrote: post #28

Earlier quoted context omitted.

> The annoying thing for GPU training is handling the cudNN dependency, which Google's guides are annoyingly lacking. I've found a nice workaround for that one that does not require registration with nvidia so you can automate it: ML_REPO_PKG=nvidia-machine-learning-repo-ubuntu1404_4.0-2_amd64.deb wget http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1404/x86_64/${ML_REPO_PKG} -O /tmp/${ML_RE…

I'm assuming from the filename that that only works if you're on Ubuntu 14.04, right?

Erm, yes, sorry! I should have noted that, but presumably there are other files for other platforms?

(these were the ones that worked for me).

16.04 is there as well:

http://developer.download.nvidia.com/compute/machine-learnin...

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

#85

Post by detaro »

canada_dry wrote: post #25
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…

> I've got the project on hold for now because I can't find a decent, non-commercial way of converting voice to text. I'd really rather not send my audio out to Amazon/Google/MS/IBM Same concern here... so my voice->text method is via android's google voice - forced to offline mode. The offline mode is surprisingly good. Re mis triggers... I also have opencv running on the same android. It only activates the voice re…

Sounds interesting, do you have a writeup or some other details somewhere? (How do you force android voice recognition to work offline? Just block the phone from the internet?)

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

#86

Post by detaro »

squeaky-clean wrote: post #71
detaro wrote: post #47

Earlier quoted context omitted.

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.

It was only mentioned in a comment. I just checked, since it never had a submission on its own I submitted it now.

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

#87

Post by nojvek »

jacquesm wrote: post #38
greenpizza13 wrote: post #36

Earlier quoted context omitted.

I strongly recommend you use Keras if you are new to Tensorflow. The API abstractions will make testing your network ideas a breeze. It won't save you from the hell of building TF, but should save you loads of time with implementation and testing.

Much appreciated, thank you!

Keras is amazing. I build tf on my raspberry pi and it was fairly easy. I'm guessing nvidia GPU's with cuDNN will get quite messy.

I would really like to see some competition in GPU space. Nvidia monopolizing deeplearning rigs may not be the best thing for the future.

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

#88

Post by coding123 »

coding123 wrote: post #77

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.

Thank you thank you Ivan Bogatyy for fixing the docker run instructions. I think it was missing the docker image name before! :)

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

#89

Post by Tpt »

syllogism wrote: post #23
minimaxir wrote: post #5

See also: spaCy, which is an open-source NLP framework that has some integration with Keras as well: https://news.ycombinator.com/item?id=13874787 ...and apparently will release a major version update today . Ouch.

Why ouch? :). It's not like there's a zero-sum game here. It's great to see more things being released, so the ecosystem can continue to improve. I do wish SyntaxNet were a bit easier to use. A lot of people have asked for SyntaxNet as a backend for spaCy, and I'd love to be using it in a training ensemble. When I tried this last year, I had a lot of trouble getting it to work as a library. I spent days trying to pas…

There is https://github.com/livingbio/syntaxnet_wrapper that does the job fairly well (I also spent days trying to be able to pass to SyntaxNet different textes without having to reload the model). Warning: installation is a bit difficult.

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

#90

Post by dmorr »

jorgemf wrote: post #20
devy wrote: post #12

"Python 3 support is not available yet." [1]. It's only supported in Python 2.7, Why? [1] https://github.com/tensorflow/models/tree/master/syntaxnet

Only for the models, the core works with python 3. I tweaked the models to use them in python 3, it is things like 'xrange and range'.

Check in a python 3 version of the code? The world will thank you!
Post reply on HN