Nowadays Artificial Intelligence seems almost equal to machine learning, especially deep learning. Some have said that deep learning will replace human experts, traditionally very important for feature engineering, in this field. It is said that two breakthroughs underpinned the rise of deep learning: on one hand, neuroscience, and neuroplasticity in particular, tells us that like the human brain, which is highly plastic, artificial networks can be utilized to model almost all functions; on the other hand, the increase in computational power, in particular the introduction of GPU and FPGA, has boosted algorithmic intelligence in a magnificent way, and has been making the models created decades ago immensely powerful and versatile. I'll add that the big data (mostly labeled data) accumulated over the past years is also relevant.

Such developments bring computer vision(and voice recognition) into a new era, but in natural language processing and expert systems, the situation hasn't seemed to have changed very much.

Achieving common sense for the neural networks seems a tall order, but most sentences, conversations and short texts contain inferences which should be drawn from the background world knowledge. Thus knowledge graphing is of great importance to artificial intelligence. Neural networks can be harnessed in building knowledge bases but it seems that neural network models have difficulty utilizing these constructed knowledge bases.

My questions are:

  • 1) Is a knowledge base (for instance a "knowledge graph" as coined by Google) a promising branch in AI? If so, in what ways KB can empower machine learning? And how can it help in natural language generation?

  • 2) For survival in an age dominated by DL, where is the direction for the knowledge base (or the umbrella term symbolic approach)? Is Wolfram-like z dynamic knowledge base the new direction? Or any new directions?

Hopefully I am asking an appropriate question here, as I was unable to tag my question as "knowledge base" nor "knowledge graph".

Am I missing something fundamental, or some idea that that addresses these issues?

  • I worked for a major IT company that at one time marketed AI products. The problem with a neural network approach is that there isn't a knowledge base per sey. So without any sort of rules, it is impossible for a neural network to explain "why." Training a neural network, then formulating rules that duplicate the network would give you such answers. But there isn't any form of machine learning that is now capable of such behavior. – MaxW Mar 6 '17 at 17:59
  • Yeah. In our company the chitchat bot supported only by NN is very very stupid. – lerner Mar 6 '17 at 23:49
  • Scientifically,one is perfectly daunting own concept! – quintumnia Mar 8 '17 at 11:17
  • I found this paper: arxiv.org/abs/1702.01932 – lerner Mar 12 '17 at 11:14
  • @lerner thanks for the paper recommendation. – Seth Simba Jan 8 at 15:48

First of all, I would like to point out the main differences between knowledge base and (Deep) machine learning, specially when the main focus is on "AI" not "Data Science":

  • NNs are like a black box; Even if they learn a dataset and gain the power of generalization over the problem domain, you'd never know how they are working. if you scrutinize the details of the developed model, all you see are digits, weights, poor and strong connections and transform functions. the "feature extraction" step before the training phase literally tells you: "hey human, enough with your complicated world, let's start zeros and ones". In the case of DL, it is worse! we do not even see what the selected and effective features are. I'm not a DL expert but as much as I know, DL's black box is darker! But knowledge bases are written in a human-friendly language. after a knowledge accumulation phase, you could see all the connections between the entities, and more important, you could interpret those connections. if you cut a wire in a knowledge base, your model will lose just a bit of its power, and you know what exactly it will lose; for example disconnecting the "Pluto" node from the "solar system" node, will tell your model what deGrasse Tyson told us. but in a ML model, this might turn it into a pure useless one: what happens if you manipulate the connection between the neuron number 14 and 47 in a NN model used to predict which planets belong to the solar system?!

  • ML models are merely an inscription of the data. They do not have the power of inference, and they don't give you one. knowledge base is on the other hand capable of inference from the prior knowledge as you indicated in your question. It is shown that DL models that have been trained with say image classification data, could also be applied to voice detection problem. But this doesn't mean DL models could apply its prior knowledge in the domain of images to the domain of voices.

  • You need kilos of data for traditional ML algorithms and tons of data for DL ones. but a single instance of a dataset will create a meaningful knowledge base for you.

There are two main research topics in NLP: machine translation and question answering. Practically it has been shown that DL works significantly with machine translation problems but acts kind of stupid in question answering challenge, specially when the domain of topics covered in the human-machine conversation is broad. Knowledge bases are no good choice for machine translation but are probably the key to a noble question answering machine. Since what matters in machine translation is only the translated version of a text (and I don't care how on earth has the machine done that as far as it is true) but in question answering problem, I don't need a parrot who repeats the same information I gave it to him, but an intelligent creature who gives me "apple is eatable" after I tell him "apple is a fruit" and "all fruits are eatable". ML models are used to elicit underneath patterns from the dataset (translation) while knowledge bases are used to extend the domain of knowns. ML models nitpick, KBs explore!

  • All fruits are edible, so long as they are not metaphoric, such the fruits "of one's labor". (Then again, we could use "devour" in a metaphoric sense, such as when one devours a "tasty" stack answer and digests its contents;) – DukeZhou Jun 6 '17 at 18:26

Your Answer

 

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Not the answer you're looking for? Browse other questions tagged or ask your own question.