Category Archives: Natural Language Processing

The latest NLP revolution

Posted on June 17, 2020 by

Read an interview with Noam Shazeer who helped spark the latest NLP revolution. “He developed the multi-headed self-attention mechanism described in “Attention Is All You Need,” the 2017 paper that introduced the transformer network. That architecture became the foundation of … Continue reading →

Posted in Natural Language Processing | Leave a comment

Extracting Data from Templatic Documents

Posted on June 12, 2020 by

In this article Google researches describe a novel approach using representation learning for tackling the problem of extracting structured information from templatic documents, such as receipts, bills, or insurance quotes. They “propose an extraction system that uses knowledge of the … Continue reading →

Posted in Human-Machine Interaction, Machine Learning, Natural Language Processing | Leave a comment

More Efficient NLP Model Pre-training

Posted on March 10, 2020 by

“Recent advances in language pre-training have led to substantial gains in the field of natural language processing, with state-of-the-art models such as BERT, RoBERTa, XLNet, ALBERT, and T5, among many others. These methods, though they differ in design, share the same idea of leveraging … Continue reading →

Posted in Natural Language Processing | Leave a comment

“Do you love me?”​ How can a computer deal with real sentences?

Posted on January 22, 2020 by

Prof. Roger Shank just published an article with this title. He writes: “My career was in Natural Language Processing which is only one part of AI. I spent my life trying to figure out ways that computers could understand sentences … Continue reading →

Posted in Artificial Intelligence, Natural Language Processing | 1 Comment

Breakthrough in Google Search

Posted on October 28, 2019 by

On Oct. 25 Pandu Nayak, Google Fellow and Vice President of Search, published an article “Understanding Searches Better Than Ever Before“.  “Search is about understanding language. The latest advancements from our research team in the science of language understanding–made possible … Continue reading →

Posted in Machine Learning, Natural Language Processing | Leave a comment

Knowledge Specification and Querying

Posted on July 25, 2019 by

Our colleagues from the Rules and Reasoning community have just reported interesting results. They built a system that achieves 100% accuracy on an extensive test suite of movie-related questions, e.g. “Who appears in a Steven Spielberg directed film?”. Their approach … Continue reading →

Posted in Natural Language Processing, Reasoning, Semantic Web | Leave a comment

Beyond Chatbots: Hyper-Personalized, Intelligent Assistants

Posted on May 7, 2019 by

Peter Voss, CEO at Aigo.ai, published the article with this name in Forbes: “Recent years have seen a proliferation of chatbots and so called ‘personal assistants.’ These supposedly serve both the convenience of the user.. However, these bots often realize poor … Continue reading →

Posted in Human-Machine Interaction, Machine Learning, Natural Language Processing | Leave a comment

Alexa for Insurers

Posted on April 2, 2019 by

Alexa, Amazon’s virtual assistant that powers Amazon’s Echo, is a tool insurance companies are using to leverage voice recognition and increase their value to their customers. Liberty Mutual offers its customers the option to use Alexa to get an auto … Continue reading →

Posted in Human-Machine Interaction, Insurance Industry, Natural Language Processing | Leave a comment

Google Announced a new Speech Recognizer

Posted on March 18, 2019 by

Google has announced the rollout of an end-to-end, all-neural, on-device speech recognizer based on the latest machine learning capabilities. “Our new all-neural, on-device Gboard speech recognizer is initially being launched to all Pixel phones in American English only. Given the … Continue reading →

Posted in Human-Machine Interaction, Machine Learning, Natural Language Processing | Leave a comment

The same Challenges for AI and Decision Models

Posted on December 17, 2018 by

Peter Voss just quoted this Harvard Business Review’s article: “The scientific community is good at building AI models that perform a single task really well. But more intuitive, conversational, and contextual interfaces will require an AI model that learns continuously — … Continue reading →

Posted in Artificial Intelligence, Decision Modeling, Natural Language Processing | Leave a comment