Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 4 years ago.
Improve this question
I am a sort of newbie to NLP world.
But anyway, I have just started my NLP project.
My task is about inferring hidden sentence in a paragraph.
Let me show you an example question.
a multiple choice question about inferring a clause in the blank
I want my machine learning model to extract some meaningful phrase from the given text(in above image, a paragraph)
I know that my question sounds quite ambiguous for you all. I just want to know even a small clue.
Thank you for your response in advance.
Skip-thought vectors are a system for predicting sentences from a context, by essentially constructing sentence-wide vectors. Might be useful, especially so in combination with context2vec if you want to build a custom model.
Related
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 1 year ago.
Improve this question
I am working on a project to use a pre-trained model and finetune it for customized language translations, for example from English to French. Is it possible to load these models in Tensorflow and run them to see how translations turn out and fine-tune afterward?
Probably the fastest way to do so is relying on the HuggingFace transformers library. If you're not familiar with it, you may take a look at their official documentation. To fine-tune a BART for NMT you can use directly this provided script (it works with some other pre-trained models too).
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 3 years ago.
Improve this question
I need a dataset for my future project based on image processing, hand recognition. I need a minimum of 5 hand position and orientation and a minumim of 200 images per set.
I want to know if there are websites where I can find a great variety of datasets.
I recommend you to search here: http://homepages.inf.ed.ac.uk/rbf/CVonline/Imagedbase.htm#gesture.
I needed this for a project too and I found a lot of variations here. It also depends on what kind of gestures you are looking for, but I think you will find here what you need.
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 6 years ago.
Improve this question
Does anyone know of or have a good tool for labeling image data to be used in training a DNN?
Specifically labeling 2 points in an image, like upperLeftCorner and lowerRightCorner, which then calculates a bouding box around the specified object. That's just an example but I would like to be able to follow the MSCoco data format.
Thanks!
You might try LabelMe, http://labelme.csail.mit.edu/Release3.0/
It's usually for outlines for segmentation, but I'm pretty sure it works fine for bounding boxes too.
I had a similar issue finding a tool that did bouding boxes for labeling image data, so I started this new project called LabelD (https://github.com/sweppner/labeld) that uses NodeJS and focuses on bouding boxes for annotation. It's still very much in alpha, but it's pretty easy to use and functional for labeling images!
Let me know if you have any questions!
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 8 years ago.
Improve this question
I need to extract text from articles online for an ios app I am developping. Is there something similar to goose that extracts just the article from the html for Swift?
It's very interesting subject. I'm not pretty sure, but it seems to be not an easy job to do. Recently Ivan Titov told about "Inducing Semantic Representations from Text with Little or No Supervision." You can see this presentation here: https://events.yandex.ru/lib/talks/2728/ (in English.)
So, our team recently took part in Swift-hackathon by CocoaHeads Moscow for this subject, but not very good result were earned. We developed recursive grabber and other cool things, but can't attain the goal. If you want to contribute to that project, look at this repo: https://github.com/CocoaHeadsMsk/hawking
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 8 years ago.
Improve this question
I have found OpenCV code that uses CvGaussBGStatModelParams structure, cvCreateGaussianBGModel, and other related functions. However, I haven't been able to find any explanations for how they work and how they are to be used and what they mean.
Any help would be appreciated.
These functions are undocumented (at least as far as the manual goes). However, if you look around in the source, you will find them in src/cvaux/cvbgfg_gaussmix.cpp. In there:
This is based on the "An Improved
Adaptive Background Mixture Model for
Real-time Tracking with Shadow
Detection" by P. KaewTraKulPong and R.
Bowden
http://personal.ee.surrey.ac.uk/Personal/R.Bowden/publications/avbs01/avbs01.pdf
The windowing method is used, but not
the shadow detection. I make some of
my own modifications which make more
sense. There are some errors in some
of their equations.
That link is probably a good start for you.