vectors – AI in Media and Society

Figuring It Out: Transformers for NLP

May 14, 2021May 14, 2021 Mindy McAdams

It was a challenge for me to figure out how to teach non–computer science students about word vectors. I wanted them to have a clear idea of how words and their meanings are represented for use in an AI system — otherwise, I worried they would assume something like a written dictionary with text and definitions. I also wanted them to know that it wasn’t something simple like “each word has a numerical code assigned to it.” So we spent some time talking about what a vector is and what “n-dimensional space” means.

*Slide above by Mindy McAdams (copyright © 2021)*

Now I need to work out how to teach them about transformers. I found a surprisingly clear article at Orange.com (formerly France Télécom), on their Hello Future website about research and innovation. I’m going to quote a large section from that article:

“Originally, in 2013, word embeddings (such as Word2Vec, Glove, or Fasttext) were able to capture representations of words in the form of vectors taking into account the context of neighboring words in large volumes of text. Two words appearing in similar contexts were ‘embedded’ into N-dimensional space, to neighboring points in this space. This approach has led to significant advances in the field of NLP, but also has its limitations. From 2018 a new way of generating these word vectors emerged. Rather than selecting the vector of a word in a previously learnt static ‘dictionary,‘ a model is responsible for dynamically generating the vector representation of a word. A word is thus projected to a vector not only according to its prior meaning, but also according to the context in which it appears. The models for effective realization of these contextual projections (BERT, ELMO and derivatives, GPT and its successors) are based on a simple yet powerful architecture called Transformer.” (Spelling and punctuation edited for American English.)

I know that paragraph might not make sense if you haven’t already learned about word vectors. The key is that transformers are able to build on and enhance the machine accuracy of what a word or sentence means by taking into account its context in the current data. So you do have a language model, previously trained on a large corpus, but the transformer analyzes the present text input in a more holistic way, transforming the vectors as it goes.

Again quoting from the Orange.com article: “While previous approaches … could model contextual dependencies, they were always constrained by referencing words by their positions [in the sentence]. Attention is about referencing by content. Instead of looking for relationships with other words in the context at given positions, attention allows you to search for relationships with all words in the context, and through a very effective implementation, it allows you to rely on the most similar words to improve prediction, whatever their position in context.”

The role of the attention module is explained in a 2017 paper that, according to Google Scholar, has been cited more than 20,000 times: Attention Is All You Need. See the PDF for diagrams of the Transformer network architecture.

Language models produced by transformers include BERT (developed by Google, and which powers Google searches), ELMo, and GPT-3. These so-called large language models have raised many concerns, particularly around ethics, as their interior processes are a black box, and their immense training data has included biased and toxic texts. The Orange.com article includes two charts that illustrate differences among BERT, ELMo, and three generations of GPT.

An important aspect of transformers is that they produce these large language models from unlabeled data, and when developing applications based on transformers and such models, good results can be obtained with only a small amount of additional training data (“few-shot learning”).

Orange — like many other companies — is using large language models for classification and information-extraction tasks such as: “sentiment analysis, personal data detection, detection and identification of named entities, syntactic dependency analysis, semantic parsing, co-reference resolution,” and question answering. These tasks involve customer-service applications as well as internal data analysis.

Much of this post is based on the article The GPT-3 language model, revolution or evolution? (February 2021).

AI in Media and Society by Mindy McAdams is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Include the author’s name (Mindy McAdams) and a link to the original post in any reuse of this content.

Encoding language for a machine learning system

September 28, 2020 Mindy McAdams

The vocabulary of medicine is different from the vocabulary of physics. If you’re building a vocabulary for use in machine learning, you need to start with a corpus — a collection of text — that suits your project. A general-purpose vocabulary in English might be derived from, say, 6 million articles from Google News. From this, you could build a vocabulary of, say, the 1 million most common words.

Although I surely do not understand all the math, last week I read Efficient Estimation of Word Representations in Vector Space, a 2013 research article written by four Google engineers. They described their work on a then-new, more efficient way of accurately predicting word meanings — the outcome being word2vec, a tool to produce a set of word vectors.

After publishing a related post last week, I knew I still didn’t have a clear picture in my mind of where the word vectors fit into various uses of machine learning. And how do the word vectors get made, anyhow? While word2vec is not the only system you can use to get word vectors, it is well known and widely used. (Other systems: fastText, GloVe.)

How the vocabulary is created

First, the corpus: You might choose a corpus that suits your project (such as a collection of medical texts, or a set of research papers about physics), and feed it into word2vec (or one of the other systems). At the end you will have a file — a dataset. (Note, it should be a very large collection.)

Alternatively, you might use a dataset that already exists — such as 3 million words and phrases with 300 vector values, trained on a Google News dataset of about 100 billion words (linked on the word2vec homepage): GoogleNews-vectors-negative300. This is a file you can download and use with a neural network or other programs or code libraries. The size of the file is 1.5 gigabytes.

What word2vec does is compute the vector representations of words. What word2vec produces is a single computer file that contains those words and a list of vector values for each word (or phrase).

As an alternative to Google News, you might use the full text of Wikipedia as your corpus, if you wanted a general English-language vocabulary.

The breakthrough of word2vec

Back to that (surprisingly readable) paper by the Google engineers: They set out to solve a problem, which was — scale. There were already systems that ingested a corpus and produced word vectors, but they were limited. Tomas Mikolov and his colleagues at Google wanted to use a bigger corpus (billions of words) to produce a bigger vocabulary (millions of words) with high-quality vectors, which meant more dimensions, e.g. 300 instead of 50 to 100.

“Because of the much lower computational complexity, it is possible to compute very accurate high-dimensional word vectors from a much larger data set.”
—Mikolov et al., 2013

With more vectors per word, the vocabulary represents not only that bigger is related to big and biggest but also that big is to bigger as small is to smaller. Algebra can be used on the vector representations to return a correct answer (often, not always) — leading to a powerful discovery that substitutes for language understanding: Take the vector for king, subtract the vector for man, and add the vector for woman. What is the answer returned? It is the vector for queen.

Algebraic equations are used to test the quality of the vectors. Some imperfections can be seen in the table below.

*From Mikolov et al., 2013; color and circle added*

Mikolov and his colleagues wanted to reduce the time required for training the system that assigns the vectors to words. If you’re using only one computer, and the corpus is very large, training on a neural network could take days or even weeks. They tested various models and concluded that simpler models (not neural networks) could be trained faster, thus allowing them to use a larger corpus and more vectors (more dimensions).

How do you know if the vectors are good?

The researchers defined a test set consisting of 8,869 semantic questions and 10,675 syntactic questions. Each question begins with a pair of associated words, as seen in the highlighted “Relationship” column in the table above. The circled answer, small: larger, is a wrong answer; synonyms are not good enough. The authors noted that “reaching 100% accuracy is likely to be impossible,” but even so, a high percentage of answers are correct.

I am not sure how the test set determined correct vs. incorrect answers. Test sets are complex.

Mikolov et al. compared word vectors obtained from two simpler architectures, CBOW and Skip-gram, with word vectors obtained from two types of neural networks. One neural net model was superior to the other. CBOW was superior on syntactic tasks and “about the same” as the better neural net on the semantic task. Skip-gram was “slightly worse on the syntactic task” than CBOW but better than the neural net; CBOW was “much better on the semantic part of the test than all the other models.”

CBOW and Skip-gram are described in the paper.

Another way to test a model for accuracy in semantics is to use the data from the Microsoft Research Sentence Completion Challenge. It provides 1,040 sentences in which one word has been omitted and four wrong words (“impostor words”) provided to replace it, along with the correct one. The task is to choose the correct word from the five given.

Summary

A word2vec model is trained using a text corpus. The final model exists as a file, which you can use in various language-related machine learning tasks. The file contains words and phrases — likely more than 1 million words and phrases — together with a unique list of vectors for each word.

The vectors represent coordinates for the word. Words that are close to one another in the vector space are related either semantically or syntactically. If you use a popular already-trained model, the vectors have been rigorously tested. If you use word2vec to build your own model, then you need to do the testing.

The model — this collection of word embeddings — is human-language knowledge for a computer to use. It’s (obviously) not the same as humans’ knowledge of human language, but it’s proved to be good enough to function well in many different applications.

Imagining words as numbers in n-dimensional space

September 24, 2020 Mindy McAdams

The vocabulary of a neural network is represented as vectors — which I wrote about yesterday. This enables many related words to be “close to” one another, which is how the network perceives similarity and difference. This is as near as a computer comes to understanding meaning — which is not very near at all, but good enough for a lot of practical applications of natural language processing.

A previous way of representing vocabulary for a neural network was to assign just one number to each word. If the neural net had a vocabulary of 20,000 words, that meant it had 20,000 separate inputs in the first layer — the input layer. (I discussed neural nets in an earlier post here.) For each word, only one input was activated. This is called “one-hot encoding.”

Representing words as vectors (instead of with a single number) means that each number in the array for one word is an input for the neural net. Among the many possible inputs, several or many are “hot,” not just one.

As I was sorting this in my mind today, reading and thinking, I had to think about how to convey to my students (who might have no computer science background at all) this idea of words. The word itself doesn’t exist. The word is represented in the system as a list of numbers. The numbers have meaning; they locate the the word-object in a mathematical space, for which computers are ideally suited. But there is no word.

Long ago in school I learned about the signifier and the signified. Together, they create a sign. Language is our way of representing the world in speech and in writing. The word is not the thing itself; the map is not the territory. And here we are, building a representation of human language in code, where a vocabulary of tens of thousands of human words exists in an imaginary space consisting of numbers — because numbers are the only things a computer can use.

I had a much easier time understanding the concepts of image recognition than I am having with NLP.