Sebastian Ruder recently wrote an article on The Gradient and asserted that the oracle of natural language processing is emerging. While I am not sure such confident statement is overstated, I do look forward to the moment that we will download pre-trained embedded language models and transfer to our use cases, just like we are using pre-trained word-embedding models such as Word2Vec and FastText.

I do not think one can really draw a parallelism between computer vision and natural language processing. Computer vision is challenging, but natural language processing is even more difficult because the tasks regarding linguistics are not limited to object or meaning recognition, but also human psychology, cultures, and linguistic diversities. The objectives are far from being identical.

However, the transferrable use of embedded language models is definitely a big step forward. Ruder quoted three articles, which I would summarize below in a few words.

• Embeddings from Language Models (ELMo, arXiv:1802.05365): based on the successful bidirectional LSTM language models, the authors developed a deep contextualized embedded models by collapses all layers in the neural network architecture.
• Universal Language Model Fine-Tuning for Text Classification (ULMFiT, arXiv:1801.06146): the authors proposed a type of architectures that learn representations for specific tasks, which involve three steps in training: a) LM pre-training: learning through unlabeled corpus with abundant data; b) LM fine-tuning: learning through labeled corpus; and c) classifier fine-tuning: transferred training for specific classification tasks.
• OpenAI Transformer (article still in progress): the author proposed a simple generative language model with the three similar steps in ULMFit: a) unsupervised pre-training: training a language model that maximizes the likelihood of a sequence of tokens within a context window; b) supervised fine-tuning: a supervised classification training that maximizes the likelihood using the Bayesian approach; c) task-specific input transformations: training the classifiers on a specific task.

These three articles are intricately related to each other. Without abundant data and good hardware, it is almost impossible to produce the language models. As Ruder suggested, we will probably have a pre-trained model up to the second step of the ULMFit and OpenAI Transformer papers, but we train our own specific model for our use. We have been doing this for word-embedding models, and this approach has been common in computer vision too.

The 2016 US Presidential Election ended with a surprise that Mr. Donald Trump won, despite the overwhelming prediction of a Clinton victory. There have been many studies challenging the theories in traditional political forecasting.

Some took an approach regarding statistics. Many studies concluded that many election forecasting models did not take into account between individual states predictions. However, a classical computation method limited such type of models that connects individual states (or fully-connected models). Hence, a group from QxBranch and Standard Cognition resorted to adiabatic quantum computation. (See: arXiv:1802.00069.)

D-Wave computers are adiabatic quantum computers that perform quantum annealing. A D-Wave 2X has 1152 qubits, and can naturally describes a Boltzmann Machine (BM) model, equivalent to Ising model in statistical physics. The energy function is described by:

$E[\mathbf{s}] = -\sum_{\mathbf{s}_i \in \mathbf{S}} b_i s_i - \sum_{\mathbf{s}_i, \mathbf{s}_j \in \mathbf{S}} W_{ij} s_i s_j$ ,

where $\mathbf{s}$ are the values of all qubits (0, 1, or their superpositions). The field strength $b_i$ and coupling constants $W_{ij}$ can be tuned. Classical models can handle the first term, which is linear; but the correlations, described by the second term, can be computationally costly for classical computers. Hence, the authors used a D-Wave quantum computer to trained the election models from June 30, 2016 to November 11, 2016 for every two weeks, and retrieved the correlations between individual states. Then The correctly simulated that Mr. Trump would win the election.

This Ising model of election was devised after the election, and it is prone to suspicion for fixing the problems using the results. However, this work demonstrated the power of a quantum computer that it solves some political modeling problems that can be too complicated for classical computers.

Quantum computation was proposed initially partly to simulate the physical universe because of the likeness of the nature and quantum systems. Some experimental simulations of Hawking radiation or Kibble-Zurek mechanisms were carried out in condensed matter systems, but they are simply too expensive to carry out. However, some scientists performed simulations on molecular systems using a quantum computer with an array of superconducting qubits. They performed the electronic structure calculation, as reported in “Scalable Quantum Simulation of Molecular Energies,” published in Physical Review X. Later, Google’s Quantum AI Team, Microsoft’s QuArC Team, and Caltech reports their work on simulating electronic structure using a quantum computer, that reduces running time but increases accuracies. Their work was reported in “Low-Depth Quantum Simulation of Materials,” also published in Physical Review X. The same team, adding a Harvard’s group, further studied the application of these molecular systems lined up as a linear array to design algorithms in quantum computers. It is reported in “Quantum Simulation of Electronic Structure with Linear Depth and Connectivity,” published in Physical Review Letters.

These people published an open-source software package, a Python library, called OpenFermion. It facilitates simulation of quantum algorithms in fermionic systems.

For a completeness, a few years ago, another group of scientists published a Python package, QuTiP, that helps simulating the open quantum systems.

Google launches her AutoML project last year, in an effort to automate the process of seeking the most appropriate neural net designs for a particular classification problem. Designing neural networks have been time consuming, despite the use of TensorFlow / Keras or other deep learning architecture nowadays. Therefore, the Google Brain team devised the Neural Architecture Search (NAS) using a recurrent neural network to perform reinforcement learning. (See their blog entry.) It is used to find the neural networks for image classifiers. (See their blog entry.)

Apparently, with a state-of-the-art hardware, it is of Google’s advantage to perform such an experiment on the CIFAR-10 dataset using 450 GPUs for 3-4 days. But this makes the work inaccessible for small companies or personal computers.

Then it comes an improvement to NAS: the Efficient Neural Architecture Search via Parameter Sharing (ENAS), which is a much more efficient method to search for a neural networks, by narrowing down the search in a subgraph. It reduces the need of GPUs.

While I do not think it is a threat to machine learning engineers, it is a great algorithm to note. It looks to me a brute-force algorithm, but it needs scientists and engineers to gain insights. Still, I believe development of the theory behind neural networks is much needed.

There are many tasks in natural language processing that are challenging. This blog entry is on text summarization, which briefly summarizes the survey article on this topic. (arXiv:1707.02268) The authors of the article defined the task to be

Automatic text summarization is the task of producing a concise and fluent summary while preserving key information content and overall meaning.

There are basically two approaches to this task:

• extractive summarization: identifying important sections of the text, and extracting them; and
• abstractive summarization: producing summary text in a new way.

Most algorithmic methods developed are of the extractive type, while most human writers summarize using abstractive approach. There are many methods in extractive approach, such as identifying given keywords, identifying sentences similar to the title, or wrangling the text at the beginning of the documents.

How do we instruct the machines to perform extractive summarization? The authors mentioned about two representations: topic and indicator. In topic representations, frequencies, tf-idf, latent semantic indexing (LSI), or topic models (such as latent Dirichlet allocation, LDA) are used. However, simply extracting these sentences out with these algorithms may not generate a readable summary. Employment of knowledge bases or considering contexts (from web search, e-mail conversation threads, scientific articles, author styles etc.) are useful.

In indicator representation, the authors mentioned the graph methods, inspired by PageRank. (see this) “Sentences form vertices of the graph and edges between the sentences indicate how similar the two sentences are.” And the key sentences are identified with ranking algorithms. Of course, machine learning methods can be used too.

Evaluation on the performance on text summarization is difficult. Human evaluation is unavoidable, but with manual approaches, some statistics can be calculated, such as ROUGE.

When it was proposed that GAN uses Wasserstein distance as the training metric, GAN is usually seen as a transportation problem. Previously, it was mentioned in a previous post that GAN can be seen as a transportation problem, and because of that, some computation can be simplified by relating a kernel in the discriminator and the generator.

GAN can be used in word translation problem too. In a recent preprint in arXiv (refer to arXiv:1710.04087), Wasserstein GAN has been used to train a machine translation machine, given that there are no parallel data between the word embeddings between two languages. The translation mapping is seen as a generator, and the mapping is described using Wasserstein distance. The training objective is cross-domain similarity local scaling (CSLS). Their work has been performed in English-Russian and English-Chinese mappings.

It seems to work. Given GAN sometimes does not work for unknown reasons, it is an excitement that it works.

Recently, Geoffrey Hinton and his colleagues made the article about capsules available. He has been known to heavily criticize the use of pooling and back propagation.

“A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or object part.” The nodes of inputs and outputs are vectors, instead of scalars as in neural networks. A cheat sheet comparing the traditional neurons and capsules is as follow:

Based on the capsule, the authors suggested a new type of layer called CapsNet.

Huadong Liao implemented CapsNet with TensorFlow according to the paper. (Refer to his repository.)

The theory and the interpretability of deep neural networks have always been called into questions. In the recent few years, there have been several ideas uncovering the theory of neural networks.

# Renormalization Group (RG)

Mehta and Schwab analytically connected renormalization group (RG) with one particular type of deep learning networks, the restricted Boltzmann machines (RBM). (See their paper and a previous post.) RBM is similar to Heisenberg model in statistical physics. This weakness of this work is that it can only explain only one type of deep learning algorithms.

However, this insight gives rise to subsequent work, with the use of density matrix renormalization group (DMRG), entanglement renormalization (in quantum information), and tensor networks, a new supervised learning algorithm was invented. (See their paper and a previous post.)

# Neural Networks as Polynomial Approximation

Lin and Tegmark were not satisfied with the RG intuition, and pointed out a special case that RG does not explain. However, they argue that neural networks are good approximation to several polynomial and asymptotic behaviors of the physical universe, making neural networks work so well in predictive analytics. (See their paper, Lin’s reply on Quora, and a previous post.)

# Information Bottleneck (IB)

Tishby and his colleagues have been promoting information bottleneck as a backing theory of deep learning. (See previous post.) In recent papers such as arXiv:1612.00410, on top of his information bottleneck, they devised an algorithm using variation inference.

# Generalization

Recently, Kawaguchi, Kaelbling, and Bengio suggested that “deep model classes have an exponential advantage to represent certain natural target functions when compared to shallow model classes.” (See their paper and a previous post.) They provided their proof using generalization theory. With this, they introduced a new family of regularization methods.

# Geometric View on Generative Adversarial Networks (GAN)

Recently, Lei, Su, Cui, Yau, and Gu tried to offer a geometric view of generative adversarial networks (GAN), and provided a simpler method of training the discriminator and generator with a large class of transportation problems. However, I am still yet to understand their work, and their experimental results were done on low-dimensional feature spaces. (See their paper.) Their work is very mathematical.

In their paper, Kawaguchi, Kaelbling, and Bengio explored the theory of why generalization in deep learning is so good. Based on their theoretical insights, they proposed a new regularization method, called Directly Approximately Regularizing Complexity (DARC), in addition to commonly used Lp-regularization and dropout methods.

This paper explains why deep learning can generalize well, despite large capacity and possible algorithmic instability, nonrobustness, and sharp minima, effectively addressing an open problem in the literature. Based on our theoretical insight, this paper also proposes a family of new regularization methods. Its simplest member was empirically shown to improve base models and achieve state-of-the-art performance on MNIST and CIFAR-10 benchmarks. Moreover, this paper presents both data-dependent and data-independent generalization guarantees with improved convergence rates. Our results suggest several new open areas of research.