Rosarie:
u want to become baby mama 2.u lack self control and that is the truth.how can u allow such discussions in the first place.u re just sex starved and what u guys have is lust.betterbstop this rubbish talk and cut him off.u re like a senior sis to him

Ageism on female is not right.
Switch their places; if it was a 38 year old guy with a 26 year old lady, it wouldn't have been much of an issue.

odizeey:
Please can someone help me on bow to download and install python, d one I downloaded is telling me error 0x80240017.

That's windows wahala.
Download Python 3.4

SoftEng:


Alright. Good luck.

Thanks

You should also checkout http://www.maluuba.com/research/ as suggested by osarenomaspecial

Sure.

victorazyvictor:
All these inconsequential questions are always up because children of this age refuses to study Bible..

And is a shame no one here with meaningful answer and they claimed to be Christians. chai

Go and read 1Corinthian 12:1-14
You will understand.

That scripture does not explain anything.
Any random pastor or prophet would also claim there are bestowed with all of the gifts of the Holy Spirit. 1 Corinthians 12:31

ScienceWatch:
Thank you Sir. Compliments of the season to you too, and your entire family.

Thanks.

You won't get what you are expecting from those two courses in Nigerian Universities even the Private ones.

I'd advice that if you're that financially fit, you go to Capetown, Norway, Denmark, Poland, Russia or any other country were you would get most out of your expectations.

However, you can take out some money to study online courses for computer hardware or software related courses, while you go through your normal course of study in the university.

budaatum:

You haven't engaged with him long enough. Read some of his postings and report back please.

Lol

AnonyNymous:

Lol

Compliments of the season guys.

ScienceWatch:
Aaaah, thank you Sir. You are really flattering me know. I have taken the test five times. Now I am broke.

I am proud of my IQ, it is cheaper that way. It has kept me alive till now, even though Satanists like Richard Dawkins and Harris lurk around every corner.

Hmm, I would advice that you don't say the result of this test at work or among professionals to avoid embarrasment.
And will honestly ask that you see a Counsellor or Psychologist, just in case...

ScienceWatch:
It will easily be agreed that every belief/disbelief has consequences, right. Good now we can safely move forward. I am highlighting the consequences of the Prophet of modern day Atheism's disbelief in God. It is more than a disbelief, it is a burning hatred for God that can motivate Atheisms prophet to go and influence another country to ban children under
13 yrs from entering a church to worship God. This is extremely cruel.

It is a burning hatred for God that Dawkins align himself with man to man marriage and the resultant stinky anal penetrations and resultant childless couples. He is showing God the finger now, but his time has come. This world recognized Satanist Dawkins is know for whipping up his followers into a frenzy to destroy the sacred doctrines of innocent peoples of the world.

There you have it. It can not be more simple and clear to any right thinking person that the consequences of Atheism is the destruction of all that is good and wholesome to humanity.

Kingebukasblog must never change the rules of this liberating challenge. He must respect the evidence of the dark and evil nature of the
Satanist Prophet of Atheism, Richard Dawkins.

Ok ooo.

ScienceWatch:
Yes IQ 27 I am afraid to admit. my dream was to have IQ 45 but there are guys here that are keeping me back oo

I'm very certain that you are mistaken Sir.
You can go take the test again for confirmation.

And I personally don't regard IQ tests as a measure of intelligence, it does not make so much sense to me.
But in any case, it's just hard to believe that your IQ is below 50.

ScienceWatch:
Firstly, the rules of the OP is sound and fair across the board.

Seconly, Kingebukasblog will do well to consider the following in formulating his definition of modern Atheism ;

The modern day prophet of Atheism, Richard Dawkins has engineered the bleak future of Finland. Now no children under 13yrs can be taught about God or enter a church, but Men who lustfully penetrate other men's excrement can now LEGALLY Marry.

Now women can also marry women. Sales of battery operated Dongles/plasic joysticks is projected to be a top seller in Finland because of the modern prophet of Atheism's Satanic influence in this unsuspecting country.

This brief example points to evidence that Atheism is founded on destructive Satanic spiritual forces. Atheism has been pressuring sane humanity to accept Satanic practices as normal, child pornography, anal sex, men marrying men, women marrying women, the destruction of all sacred doctrines and many more.

You say the future of Finland is bleak, na wa oo, have you analysed the crime rate there to a very religious country like Nigeria even Israel sef.

And your illustration does not cover atheism, atheism is simply a disbelieve in a God, that's all, any extra "satanic activities" according to you are from the hearts of men.

ScienceWatch:
Thanks Sir. Thats why I can communicate so well with Low-Level Atheists world wide.

Uhmm...
Please look at your post again.
Did you mean 27 or 270.

Any matured man with IQ lower than 50 is mentally challenged.

Where did you take your IQ test or are you referring to a context i'm not aware of?

odizeey:
Im interested

Here's the link to contribute to: https://www.nairaland.com/4237475/artificial-intelligence-machine-learning-group

@neahyo At last.

KingEbukasBlog your definition of atheism has been refuted.
So what's the point of number 2, are you trying to shoot yourself in the foot.

I don't know if this challenge is still on, it would have been fun to debate number 1 with you, but it might just end up in a stalemate.

And i support budaatum request of a judge though.

ScienceWatch:
I also have a high IQ of 27, so what are they bragging about? Besides, there is something far superior than intelligence, IT IS WISDOM.

Wisdom cannot be gained by memorizing exam papers, nor from ignoring a challenge such as this one offered by a truly WISE man and esteemed Nairalander, Kingebukasblog.

Wow, you seriously have a "high" IQ of 27.

That's interesting.

islamics:
In my own view: personally, I would prefer Telegram because it is more Developer friendly and the audience could be worldwide. Though WhatsApp has more users. Again, Telegram has API for those that might want to play with it. One of the reason why I think WhatsApp group die easily is that they are yet to allow incorporating of bot into the app (though I don't know if they have) . For instance, in telegram, in some group when you join; you are welcome by a bot. In some cases, a bot provide updates on different materials. And there is a pinned message available to user. Again new user can see previous message in a group unlike WhatsApp.
Any one decided on is welcome. Even though, it is slack.

I agree with this, whatsapp is not a good platform for a group like this.
I've never used telegram though, but from this explanation i think Slack or Telegram would be Okay.

Though I'm mostly used to Slack.

SoftEng:


I didn't want to comment on this because of my limited knowledge in NLP. The only area(task) that I have dabbled into in the past is Language Modeling. However, from what I remember Question Answering Systems (QAS) are still very much limited as researchers have not been able to get it to practically work well on open ended domain. This does not mean that it doesn't work, but it just very hard right now. It's does not work practically well compared to Language Translation task which works well.

Here's something that maybe useful to you. Amazon hosts an Alexa Prize competition (https://developer.amazon.com/alexaprize) for universities around the world to build a conversational agent (which is atleast similar to QAS, if not thesame). You can check out the 2017 prize winner and read through their paper or blog post (if available) to see the techniques used. Who knows, if they decide to open it to candidates outside universities, you can form a group here that can participate as well.

Below are 2 additional links (not related to the competition) that you might find useful
https://aws.amazon.com/blogs/ai/creating-a-question-and-answer-bot-with-amazon-lex-and-amazon-alexa/
https://aws.amazon.com/blogs/aws/announcing-the-aws-chatbot-challenge-create-conversational-intelligent-chatbots-using-amazon-lex-and-aws-lambda/

[url]Question[/url]
Do you have any dataset in mind that you want to use to train your QAS?

Final Note
I once watched a video where a top NLP scientist mentioned that QAS are like crown jewel of NLP because a fully functional QAS should be able to perform other NLP tasks (e.g. you can ask a QAS to translate a text from one language to another, or you can ask a QAS to summarize text)

Thanks.

The usual method for question answering normally revolves around the popular bag of words model, where faetures are trained using the best fit algorithm or ensemble methods, and other effective stuff come to play.

I've built some naive question answering system in time past using these methods, and POS taggers are only(or mostly) for word-category disambiguation for context meaning.
For example, the sentence; "He fishes fish", it enables the system to distinguish the verb in the statment.

What i need however is a different approach, with focus on POS taggers. I just want to see the extent a good analysis of POS taggers can be used for question answering without ngrams or bag of words model or lemmatization and so on, and because of the nature of POS taggers, i think if one is succesful in closed domain questions, open domain won't be a problem, because the algorithm won't be using a similarity metrics per say, but will actually understand the words spoken.

So this is more of a research to me, when i'm less busy I'll work up some stuff to see what i come up with and share with the group.

I've used POS taggers for speech synthesis, and this was actually the only place where POS taggers really matterd the most.

SoftEng please can you help me out with my question.
Cc: osarenomaspecial whiztim umaryusuf

Hmm, politics...

raymod170:


You correct tho i used bag of words model and feed in datasets for training and naive classifier and decision trees.

but since you in need some differnt from Microsoft ai platform am sorry i cant contribute no more as my knowledge is limited to Microsoft ai platform among other things #Proudly.Net LOL

Best regards

Thanks.

raymod170:


closed domain questions focuses on a single domain eg Hotel, where you ask the system questions about hotels and they system responds with answers from a data source which must be created to suite the close ended questions

if you just understand what i just typed you would agree with me that it focuses on descriptive results.

i implemented this model along with other models on my own personal assistant
https://www.nairaland.com/4125501/vee-personal-assistant-new-update

which as i said earlier Microsoft platform can also be used to achieve

best regards

Great project.
I understand your explanation of closed domain questions.
But Microsoft AI platform should be similar to wit.ai and IBM Watson api, were you are to feed in datasets for training and possibly using naive classifier and decision trees.

Or did you use pos taggers in your approach(without using bag of words model)?

Unmarshalled:
OK so where should I start, I have basic knowledge of python

Hmm, SoftEng over to you.

Check this web post for an overview of ML and some interseting ML algorithms.

Pick anyone and learn and let's work on a project here.

raymod170:


if am to work on the project I would pick closed domain questions its easier to create POST with

as for the listed platforms I am sorry am a Microsoft person lol but Microsoft AI platform isn't bad at all

Nah, i don't need the usual "intent/entity" approach. Correct me if i'm wrong, I've not used Microsoft AI before but i think this is how they roll too.

What i need is for the system to be able to identify a question and the subject of the question based on the part of speech structure of the sentence?

Edit:

if am to work on the project I would pick closed domain questions its easier to create POST with

How easy do you mean?

raymod170:


would the questions be closed domain or they would be open domain questions

Any.

Also what platform do you want it to be developed on

Anyone you're comfortable with but if you can preferably Python, Matlab, Octave or R.

First to comment.

Can anyone with knowledge of NLP build a question answering system with just part of speech tagging?
Please if you can or have insight on how to go about it, discuss with the group.

Beosten:


It's like a messenger but the idea is different.

Hmm, hope you get a good developer.
Good luck.


I don't like the stress of developing app, i could use that time to play with maths.
I'm a data science/machine learning programmer, so i might not be a good fit for your task.

Beosten:


What I'm trying to develop may even be impossible. But I still think it's possible. So, someone that's been coding for years should hear me out.

Is it machine learning related?

SoftEng:
@4kings, @Unmarshalled and @everyone. I apologise for the delays.

Since we have more than 10 persons interested in the group, I'll go ahead an create a thread now on Nairaland as earlier stated.

@4kings thanks for your inputs so far.

Atlast.

Beosten:
Can you link me up with a developer?

I've given you links already to create your quick prototype without any coding experience.

I'm not saying you shouldn't get a developer but since you intended to try yourself why not check one of those links out.

Try using MIT AppInventor2 or AppyPie or Unreal Engine and so on.

Unmarshalled:
Hey guys, I'm interested in machine learning but I have zero knowledge apart from its definition.

Let's wait for SoftEng.

You can start with some courses from MIT OpenCourseWare.

Yoshy:


What if use first Bank visa gold card (dollar dominated)?

That would not work.
it has a Nigerian billing address.