NLP’s generalization problem, and how researchers are tackling it

To be fair, poor generalisation is not a problem of NLP, but of NLP using deep neural networks, which is a very recent phenomenon, following from the success of deep learning for image and speech processing.<p>If you asked me (you shouldn&#x27;t, I&#x27;m biased), I&#x27;d tell you that we&#x27;re never going to get deep neural nets to behave well enough to learn meaning. Those damn things are way too smart for us. They&#x27;re so smart that they can always find the easiest, dumbest way to map inputs to outputs- by simply overfitting to their training set (or their entire data set, if cross-validation is thorough enough). You can see lots of examples of that in the article above.<p>The big promise of deep learning was (and is) that it would free us from the drudgery of feature engineering- but, the amount of work you need to do to convince a deep net to learn what you want it to, rather than what it wants to learn, is starting to approach that of hand-crafting features.<p>And we still don&#x27;t have language models that make any sense at all.

I&#x27;m not sure we read something as much as we develop a shared mental model and associated new language with another human. Most of the time these models are just slightly different from before, so the change is so subtle as to be invisible. We have the appearance of a universal language called, say, &quot;English&quot;. We don&#x27;t actually have one. It&#x27;s close enough.<p>If you take a look around, printed words don&#x27;t exist in most languages. Most languages are spoken. Printing is an extremely new thing we&#x27;ve only had for a very short amount of time. The only thing print can do is present a stilted, over-formal version of what listening to a monotone person give a speech in a dark room might be like. That&#x27;s good enough for most cases, since the brain makes stuff up it needs. But I don&#x27;t think it&#x27;s language, at least not in the same way real spoken languages are language. Real languages are a messy and confusing affair, even more than printed words can be. The way it works is through the interaction over time, not over definitions. (Something something language games)<p>I wish the guys luck. I&#x27;m not so sure we understand the problem yet. We may end up creating a machine that makes up answers to our questions after reading such that it sounds like a real person is doing the work. That&#x27;s cool -- but it&#x27;d be a horrible disaster for humanity if something like that started being the primary interaction point with people. Over time it would make us a horribly stupid and unimaginative species. Like everything else in tech, we have good intentions and endless optimism. We&#x27;re going to solve a problem whether we understand what it is or not, dang it. plus ça change... (And no, I don&#x27;t think giving up the idea is any good. I&#x27;m just encouraging more understanding of the real goal versus the apparent goal)

&quot;a mouth without a brain&quot; analogy is good one. Current NLP is impressive but there are limits.<p>People have spatiotemporal model of the world, different physical models, social and behavioral models of the world, organizational model of the society, economic model, etc. Humans parse the language and transform it into multiple models of the world where many indented meanings and semantics are self-evident and it becomes &quot;a common sense&quot;. They have crude understanding of how fabrics, paper, gas, liquid, rubber, iron, rock, etc. behave and they understand written text based on this more complete model zoo.<p>There is similar limit in computer vision. Humans reason about 2d images using internal 3d model. Even if they see a completely new object shape, they can usually infer what the other side of the object looks like using basic symmetries and physical models.<p>Image understanding must eventually transform into spatiotemporal + physical model and there are several approaches underway. NLP has much harder problem, because the problem is more abstract and complex.

Related article on the same website: <a href="https:&#x2F;&#x2F;thegradient.pub&#x2F;nlp-imagenet&#x2F;" rel="nofollow">https:&#x2F;&#x2F;thegradient.pub&#x2F;nlp-imagenet&#x2F;</a><p>NLP (or specifically NLP using deep learning) seems to be having a breakout moment in the last year or so where there have been large advancements back to back.<p>Generalization is hard - you&#x27;re often tuning millions of parameters at once, and often the most &quot;sane&quot; thing for the loss function to do is rote memorization. It&#x27;ll be interesting to see what comes about from this discussion.

Great article! It is very true that NLP is amongst the most lagging divisions within machine learning. Mainly because text content is very unstructured everywhere, let alone working consistently for different languages.<p>It is fascinating to see how things got better over the last couple of years though!

If nothing else, you should open up this article to look through the images just below intro - often surprising how non-intelligent these learned NLP models often actually are, especially for non AI-researchers.

This isn&#x27;t an NLP problem, it&#x27;s an AI problem. Despite all the hype, we haven&#x27;t actually made any progress toward solving strong AI, human-like general intelligence. NLP, computer vision, and many other AI problems are probably AI-complete, meaning that solving them entails solving strong AI. And the inability to generalize is exactly what separates the partial solutions we currently have from strong AI.

Recently there has been lot of interesting research in field of NLP. Lot of new models, algorithms and techniques have been developed along with lot of research papers published. Personally I feel that NLP is now heading in direction where we had an aha moment with ImageNet.

A thought I had the other day was how much of a driver was our need for rhythm and rhyme in the development of synonyms. Which led me to thinking how much is language driven by fun, as much as it is by any real logic. It seems word choice for any given topic is dominated by early mover and then just plain pleasant sound.<p>To that end, any system that is just looking for the logic of an underlying system is going to be stymied by the fundamental lack of it in language. There is the appearance of logic. And it can actually get you quite far. However, I question if it can encompass all of it. At least until the next best seller comes out.<p>To that end, I do not find it surprising that the best model will be an ensemble model. More, as long as we are dealing with English (a non-pictographic and a non-phonetic language), then we are ultimately trying to build a model on top of a malleable base where appeals to the logic of yesterday in a language have a non zero chance of failing today. (Edit to make this point clearer, it is amusing to me how many lines in classic Shakespear no longer pop in the same way for current language. &quot;Now is it Rome indeed, and room enough&quot;. That a pair of words could cease to be homophones is not something that seems at all obvious. Of course, I have not studied this in decades, so mayhap my grade school lied to me.)

We basically expect deep neural networks to acquire language without a body that it can use to interact with an environment. I believe you cannot separate language from the body or the environment. A corpus of text is simply not holistic enough to capture the meaning behind the symbols.

Many miles down the path where hours (slowly) lays to rest, I can imagine a vivid portrait being hung in a tree outside a dungeon. Of course created with non-existing poisonous paint. A painting of good natured, voluptuous beings huddled down and whispering to each other. Whispers that should then be set free to travel the invisible rails of the web trainset everyone play with almost everywhere. The trainset that the strict parents watches without blinking their tiny hidden trinoculars. Small talk carefully elaborated and twisted to do with the ultimate meaning as you did with the dead cat, in the backyard, but not only buried within but hidden with fragrant leafs that hasn&#x27;t been seen, smelled or heard before. Later, another image can be conjured of the train with heavy soldiers that hasn&#x27;t gotten a single flag on the journey, embarking, and upon inspection of their long seen captain, immediately recognized for their true unchanging self.