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 2 years ago.
Improve this question
please I have a university project called (automatic generation of OCL
constraints) and my supervisor asked me to choose a tool from this list of tools
for natural language processing:
Apache OpenNLP, Deeplearning4j, ChatScript, DELPH-IN, DKPro Core,
general architecture text engineering GATE, Gensim, LinguaStream,
Mallet (software project), Modular Audio Recognition Framework, MontyLingua,
Natural Language Toolkit, SpaCy, UIMA.
what would be the easiest to implement and which one would be most suitable for my future work?
else any propositions!
You should beware of a fundamental contradiction.
Users of OCL typically expect 100% accuracy.
Users of NLP are generally very pleased to achieve greater than 95% accuracy.
You must therefore restrict your domain to where 95% accuracy is acceptable, and this may influence your language choices.
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 7 years ago.
Improve this question
Has anybody seen a resource covering specifically the use of machine vision for locating a human in a room, including cases where they may be partially obscured? I know about OpenCV and other machine vision packages, but I'm looking for a paper/library/code example that focuses solidly on identifying a human in a room; something that is readily integrated into code rather than being a rough idea that would require weeks or months of tweaking or enhancing to do a reasonable job of succeeding at the task. I'd prefer something that does not require binocular vision and can work with a single camera.
First: you should read this about human detection. Then you can find/use opencv code implementing the training step of this kind of detector. You will need to access to a database for training like INRIA Person dataset.
Second: if you need to handle partial obstruction, you may need to implement a human body tracker that can handle this problem. Particle filter could do the work.
If you have problems with implementation feel free to ask more specific 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 7 years ago.
Improve this question
Good evening,
I'm working on a project with Kinect and I need to perform a gender-recognition using the voice information caught by the microphone of the sensor.
The recognition could also be text-based, i.e. the sentence said by the user could always be the same. I "just" need the binary answer male/female.
I've checked the quite popular open-source Sphinx but I can't understand if it could be used for my needs.
Any idea of what I could use?
Thanks in advance.
For sake of completeness, finally I solved the recognition task without analyzing the voice input.
Gender can be detected with an acceptable precision also by learning and then classifying visual biometric traits. I used speech recognition only as "interface" to activate the demo.
There are several ways to achieve this. You can track pitch (lower pitch values will be male, otherwise female). Or try to build a GMM (Sphinx cannot do this, but HTK can), with one model for male, other for female and another to children.
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 7 years ago.
Improve this question
I am working on a Graduation Project and wondering if anyone can help me with: Benchmark data to load and test on my application.
We are willing to compare between different designs and implementations of different database management systems, and I thought we shall use a standard data set for this task.
Is there any? and if yes, would you kindly show me where to find some, and if there are measures to consider, that would be really helpful.
Thanks in advance.
There are many standard benchmarks. The most famous are the TPC Benchmarks:
http://www.tpc.org/information/benchmarks.asp
Moreover, some researchers publish specific benchmarks. For example, O'Neil et al. avec proposed the Star Schema Benchmark. You need a small and free program to generate the data.
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 7 years ago.
Improve this question
This is the ponycorn game: http://www.untoldentertainment.com/games/sissy/
A couple of my non-programmer friends who are teachers are interested in building games with a similar look and feel with their kids.
What would be a good (the best) tool to get started with?
Independently of the particular game in question, there are some projects aiming to bring programming closer to non-programmers. The all differ in the level of abstraction though. Some of the most interesting ones :
Scratch visual, lego-like, great for kids, developed by the MIT
Lego Mindstorms provides visual programming, but I'm afraid, this is not suitable for programming ponys as it concentrates on the mindstorms robotics project.
processing - a former MIT project. Cross-platform (windows, linux, mac, android) scripting environment, is a rather thin layer over a java framework. very versatile, providing even OpenGL rendering, but your friends will have to write code still - simpler than with most other frameworks but still
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 7 years ago.
Improve this question
I remember encountering a commercial software that scanned a project's source code and provided a list of all the different software licenses it used. That is, it would find all the third party code used in a project and give their licenses (Apache, GPL, ...).
Can anyone provide a link to such a program?
Found the one I remembered:
http://www.blackducksoftware.com/protex - Protex by Black Duck.
The key term to use in google, as I learned the hard way, is "Software Compliance Management".
FOSSology is a GPL-licensed tool for analyzing OS licensing. It's main capability is to do pattern matching against uploaded source code and find matching licenses.
I know about a Ruby library called Ohcount.