Amongst the hardest problems in computer science are challenges around getting machines to understand and generate natural language. This season is an exploration of current research, applications, and thought leaders with something to say about artifical intelligence.
This episode reboots our podcast with the theme of Natural Language Processing for the next few months.
Github is many things besides source control. It's a social network, even though not everyone realizes it. It's a vast repository of code. It's a ticketing and project management system. And of course, it has search as well.
The earliest efforts to apply machine learning to natural language tended to convert every token (every word, more or less) into a unique feature. While techniques like stemming may have cut the number of unique tokens down, researchers always had to face a problem that was highly dimensional. Naive Bayes algorithm was celebrated in NLP applications because of its ability to efficiently process highly dimensional data.
In a recent paper, Leveraging Discourse Information Effectively for Authorship Attribution, authors Su Wang, Elisa Ferracane, and Raymond J. Mooney describe a deep learning methodology for predict which of a collection of authors was the author of a given document.
Word2vec is an unsupervised machine learning model which is able to capture semantic information from the text it is trained on. The model is based on neural networks. Several large organizations like Google and Facebook have trained word embeddings (the result of word2vec) on large corpora and shared them for others to use.
In the first half of this episode, Kyle speaks with Marc-Alexandre Côté and Wendy Tay about Text World. Text World is an engine that simulates text adventure games. Developers are encouraged to try out their reinforcement learning skills building agents that can programmatically interact with the generated text adventure games.
In the second half of this episode, Kyle interviews Kevin Patel about his paper Towards Lower Bounds on Number of Dimensions for Word Embeddings. In this research, the explore an important question of how many hidden nodes to use when creating a word embedding.
One of the most challenging NLP tasks is natural language understanding and reasoning. How can we construct algorithms that are able to achieve human level understanding of text and be able to answer general questions about it?
Kyle interviews Julia Silge about her path into data science, her book Text Mining with R, and some of the ways in which she's used natural language processing in projects both personal and professional.
A sequence to sequence (or seq2seq) model is neural architecture used for translation (and other tasks) which consists of an encoder and a decoder.
Machine transcription (the process of translating audio recordings of language to text) has come a long way in recent years. But how do the errors made during machine transcription compare to the errors made by a human transcriber? Find out in this episode!
While at NeurIPS 2018, Kyle chatted with Liang Huang about his work with Baidu research on simultaneous translation, which was demoed at the conference.
Bilingual evaluation understudy (or BLEU) is a metric for evaluating the quality of machine translation using human translation as examples of acceptable quality results. This metric has become a widely used standard in the research literature. But is it the perfect measure of quality of machine translation?
ELMo (Embeddings from Language Models) introduced the idea of deep contextualized word representations. It extends previous ideas like word2vec and GloVe. The ELMo model is a neural network able to map natural language into a vector space. This vector space, out of box, proved to be incredibly useful in a wide variety of seemingly unrelated NLP tasks like sentiment analysis and name entity recognition.
Modern messaging technology has facilitated a trend towards highly compact, short messages send by users who can presume a great amount of context held between the communicating parties. The rules of grammar may be discarded and often visible errors are a normal part of the conversation.
>>> Good mornink
Yet such short messages are also important for businesses whose users are unlikely to read a large block of text upon completing an order. Similarly, a business might want to offer assistance and effective question and answering solutions in an automated and ideally multi-lingual way. In this episode, we discuss techniques for designing solutions like that.
A gentle introduction to the very high-level idea of "attention" in machine learning, as it will play a major role in some upcoming episodes over the next few weeks.
This is an interview with Ellen Loeshelle, Director of Product Management at Clarabridge. We primarily discuss sentiment analysis.
When users on Twitter post with geographic tags, it creates the opportunity for a variety of interesting questions to be posed having to do with language, dialects, and location. In this episode, Kyle interviews Bruno Gonçalves about his work studying language in this way.
Kyle and Linhda discuss attention and the transformer - an encoder/decoder architecture that extends the basic ideas of vector embeddings like word2vec into a more contextual use case.
In this episode, Kyle interviews Laura Edell at MS Build 2019. The conversation covers a number of topics, notably her NCAA Final 4 prediction model.
Kyle chats with Rohan Kumar about hyperscale, data at the edge, and a variety of other trends in data engineering in the cloud.
USC students from the CAIS++ student organization have created a variety of novel projects under the mission statement of "artificial intelligence for social good". In this episode, Kyle interviews Zane and Leena about the Endangered Languages Project.
Kyle and Linh Da discuss the class of approaches called "Named Entity Recognition" or NER. NER algorithms take any string as input and return a list of "entities" - specific facts and agents in the text along with a classification of the type (e.g. person, date, place).
Priyanka Biswas joins us in this episode to discuss natural language processing for languages that do not have as many resources as those that are more commonly studied such as English. Successful NLP projects benefit from the availability of like large corpora, well-annotated corpora, software libraries, and pre-trained models. For languages that researchers have not paid as much attention to, these tools are not always available.
In 2017, Facebook published a paper called Deal or No Deal? End-to-End Learning for Negotiation Dialogues. In this research, the reinforcement learning agents developed a mechanism of communication (which could be called a language) that made them able to optimize their scores in the negotiation game. Many media sources reported this as if it were a first step towards Skynet taking over. In this episode, Kyle discusses bargaining agents and the actual results of this research.
Sebastian Ruder is a research scientist at DeepMind. In this episode, he joins us to discuss the state of the art in transfer learning and his contributions to it.
Kyle and Linhda discuss some high level theory of mind and overview the concept machine learning concept of catastrophic forgetting.
Kyle provides a non-technical overview of why Bidirectional Encoder Representations from Transformers (BERT) is a powerful tool for natural language processing projects.
Video annotation is an expensive and time-consuming process. As a consequence, the available video datasets are useful but small. The availability of machine transcribed explainer videos offers a unique opportunity to rapidly develop a useful, if dirty, corpus of videos that are "self annotating", as hosts explain the actions they are taking on the screen.
Kyle sits down with Jen Stirrup to inquire about her experiences helping companies deploy data science solutions in a variety of different settings.
Tim Niven joins us this week to discuss his work exploring the limits of what BERT can do on certain natural language tasks such as adversarial attacks, compositional learning, and systematic learning.
Omer Levy joins us to discuss "SpanBERT: Improving Pre-training by Representing and Predicting Spans".
Allyson Ettinger joins us to discuss her work in computational linguistics, specifically in exploring some of the ways in which the popular natural language processing approach BERT has limitations.
Rajiv Shah attempted to reproduce an earthquake-predicting deep learning model. His results exposed some issues with the model. Kyle and Rajiv discuss the original paper and Rajiv's analysis.
GPT-2 is yet another in a succession of models like ELMo and BERT which adopt a similar deep learning architecture and train an unsupervised model on a massive text corpus.
Manuel Mager joins us to discuss natural language processing for low and under-resourced languages. We discuss current work in this area and the Naki Project which aggregates research on NLP for native and indigenous languages of the American continent.
While at MS Build 2019, Kyle sat down with Lance Olson from the Applied AI team about how tools like cognitive services and cognitive search enable non-data scientists to access relatively advanced NLP tools out of box, and how more advanced data scientists can focus more time on the bigger picture problems.
The modern deep learning approaches to natural language processing are voracious in their demands for large corpora to train on. Folk wisdom estimates used to be around 100k documents were required for effective training. The availability of broadly trained, general-purpose models like BERT has made it possible to do transfer learning to achieve novel results on much smaller corpora.
Thea Sommerschield joins us this week to discuss the development of Pythia - a machine learning model trained to assist in the reconstruction of ancient language text.
Buck Woody joins Kyle to share experiences from the field and the application of the Team Data Science Process - a popular six-phase workflow for doing data science.
Alex Reeves joins us to discuss some of the challenges around building a serverless, scalable, generic machine learning pipeline. The is a technical deep dive on architecting solutions and a discussion of some of the design choices made.
Seth Juarez joins us to discuss the toolbox of options available to a data scientist to jumpstart or extend their machine learning efforts.
We are joined by Colin Raffel to discuss the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer".