Please join us May 24 at 1:00 pm EST/10:00 am PST for an online discussion about how recent breakthroughs in deep learning allow us to extract and process meaning from text. This opens up a vast range of applications: summarization, instant translation, semantic search, document clustering, and even speech recognition. We’ll be joined by Agolo, a startup focused on text summarization. You can register here.
Making language computable has been a goal of computer science research for decades. Historically, it has been a challenge to merely collect and store data. Today, however, it has become so cheap to store data that we often have the opposite problem. Once data has been collected, it’s now a challenge to meaningfully analyze it.
But new neural network techniques are enabling organizations to get a handle on unstructured text. As Agolo CTO Mohamed AlTantawy puts it:
Our goal is to mimic the human thought process of contextualizing real-time data. For example, if a human sees a news item about the iPhone, she will immediately identify that with her knowledge about Apple: that Tim Cook is the CEO, that the iPhone is their major product, and so on. We aim to mimic this human process algorithmically, creating what we call an AI analyst — a universally available AI that can write simple summaries from any unstructured data set.
At this event, we’ll explore AlTantawy’s comments as we discuss:
- why summarization is important now
- why summarization is a gateway to making language computable
- what the different technical approaches to summarization are and what the tradeoffs exist between them
- how companies are using summarization to research large document collections, identify breaking news, or generate compliance reports from meeting minutes
- where we think this is headed in the near future
This discussion is appropriate for non-technical business leaders who want to understand the strategic value of summarization and engineers/data scientists who want to learn how the technology works.
We look forward to hosting you on the 24th! Please send questions to email@example.com.
More from the Blog
May 3 2016
by — The Fast Forward Labs research team is developing our next prototype, which will demonstrate an application of probabilistic programming. Probabilistic programming languages are a set of high-level languages that lower the barrier to entry for Bayesian data analysis. Bayesian data analysis is often seen as the best approach to machine learning. Models derived by this process are highly interpr...
May 23 2016
by — We’re excited for tomorrow’s online discussion about automatic text summarization! You can register here. During the event, Mohamed AlTantawy, CTO of Agolo, will explain the tech behind their summarization tool. In this blog post, he describes how his team evaluates the quality of summaries produced by their system. Join us tomorrow to learn more and ask questions about the approach! Evalua...
Aug 15 2017
by — The Tabula Rogeriana, a world map created by Muhammad al-Idrisi through traveler interviews in 1154. The Wikipedia corpus is one of the favorite datasets of the machine learning community. It is often used for experimenting, benchmarking and providing how-to examples. These experiments are generally presented separate from the Wikipedia user interface, however, which has remained true to the...