AI News, Vowpal Wabbit

Vowpal Wabbit

John Langford is a machine learning research scientist, a field which he says “is shifting from an academic discipline to an industrial tool”.

His primary research interest is in understanding how to get human knowledge into a machine learning system in the most efficient way possible.

He works primarily in the areas of language (computational linguistics and natural language processing) and machine learning (structured prediction, domain adaptation and Bayesian inference).

He associates himself most with conferences like ACL, ICML, NIPS and EMNLP, and has over 30 conference papers (one best paper award in ECML/PKDD 2010) and 7 journal papers.

Jaime Carbonell

Jaime Guillermo Carbonell (born July 29, 1953) is a computer scientist who has made seminal contributions to the development of natural language processing tools and technologies.

His research spans several areas of computer science, mostly in artificial intelligence, including: machine learning, data and text mining, natural language processing, very-large-scale knowledge bases, translingual information retrieval and automated summarization.

Some of Carbonell’s major scientific accomplishments include the creation of MMR (maximal marginal relevance) technology for text summarization and informational novelty detection in search engines, invention of transformational analogy, a generalized method for case-based reasoning (CBR) to re-use, modify and compose past successful plans for increasingly complex problems and Knowledge-based interlingual machine translation.

Carbonell made major technical contributions in several fields, including (1) Creation of MMR (maximal marginal relevance) technology for text summarization and informational novelty detection in search engines,(2) Proactive machine learning for multi-source cost-sensitive active learning, (3) Linked conditional random fields for predicting tertiary and quaternary protein folds, (4) Symmetric optimal phrasal alignment method for trainable example-based and statistical machine translation, (5) Series- anomaly modeling for financial fraud detection and syndromic surveillance, (6) Knowledge-based interlingual machine translation, (7) Robust case-frame parsing, (8) Seeded version-space learning and (9) Invention of transformational and derivational analogy, generalized methods for case-based reasoning (CBR) to re-use, modify and compose past successful plans for increasingly complex problems.

The teams led by Carbonell have achieved top honors in many areas such as first scalable high-accuracy interlingual machine translation (1991), first speech-to-speech machine translation (1992), first large-scale spider and search engine (1994), and first trainable, large-scale protein-structure topology predictor (2005).

Machine Learning Group

Instead of laboriously creating a handcraftedset of filtering rules, we can use machine learning to extractpatterns that differentiate spam from ham, based solely on a collectionof messages that have been labelled as spam and ham respectively, andthen use those patterns in the filter.

It has been used to helpdetermine what information dairy farmers use in deciding which cowsto keep in their herds, been applied to bioinformatics problems such asgene interaction discovery, and been used for many other applicationssuch as mining supermarket transaction data for high profit productassociations, predicting the levels of chemicals like nitrogen and carbonin soils to aid farmers' fertilizer decisions, and processing naturallanguage to extract keywords from documents.Further details on the group can be found at: www.cs.waikato.ac.nz/~ml/

One of my current projects is exploring how the authors of academic publications behave, and what factors decide whether or not they work together.

This is done using a time series model that explicitly models how factors relating to both an author's publications and to the network of coauthors surrounding them are changing over time.

My masters thesis was turned into an instructional textbook for beginning bioinformaticists on how to do gene network inference, and provides an overview of many state-of-art algorithms and techniques along with simulated performance examples.

Natural Language Processing: Crash Course Computer Science #36

Today we're going to talk about how computers understand speech and speak themselves. As computers play an increasing role in our daily lives there has ...

The 7 Steps of Machine Learning

How can we tell if a drink is beer or wine? Machine learning, of course! In this episode of Cloud AI Adventures, Yufeng walks through the 7 steps involved in ...

Natural Language Generation at Google Research

In this episode of AI Adventures, Yufeng interviews Google Research engineer Justin Zhao to talk about natural text generation, recurrent neural networks, and ...

Dr. Yann LeCun, "How Could Machines Learn as Efficiently as Animals and Humans?"

Brown Statistics, NESS Seminar and Charles K. Colver Lectureship Series Deep learning has caused revolutions in computer perception and natural language ...

Introduction to Natural Language Processing - Cambridge Data Science Bootcamp

Talk by Ekaterina Kochmar, University of Cambridge, at the Cambridge Coding Academy Data Science Bootcamp: ...

Tensorflow, deep learning and modern RNN architectures, without a PhD by Martin Gorner

The hottest topic in computer science today is machine learning and deep neural networks. Many problems deemed "impossible" only 5 years ago have now ...

Probabilistic Machine Learning in TensorFlow

In this episode of Coffee with a Googler, Laurence Moroney sits down with Josh Dillon. Josh works on TensorFlow, Google's open source library for numerical ...

Use case for Natural Language Processing and Machine Learning.

A presentation (not technical) on Natural Language Processing and Machine Learning. Machine Learning on phone calls natural language processing use ...

Deep Learning Approach for Extreme Multi-label Text Classification

Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.

Machine Learning and Robust Optimization, Fengqi You, Cornell University

When Machine Learning Meets Robust Optimization: Data-driven Adaptive Robust Optimization Models, Algorithms & Applications In this presentation, we will ...