Summarizing text is a task at which machine learning algorithms are improving, as evidenced by a recent paper published by Microsoft. Thats good news automatic summarization systems promise to cut down on the amount of message-reading enterprise workers do, which one survey estimates amounts to 2.6 hours each day.
Not to be outdone, a Google Brain and Imperial College London team built a system Pre-training with Extracted Gap-sentences for Abstractive SUmmarization Sequence-to-sequence, or Pegasus that leverages Googles Transformers architecture combined with pretraining objectives tailored for abstractive text generation. They say it achieves state-of-the-art results in 12 summarization tasks spanning news, science, stories, instructions, emails, patents, and legislative bills, and that it shows surprising performance on low-resource summarization, surpassing previous top results on six data sets with only 1,000 examples.
As the researchers point out, text summarization aims to generate accurate and concise summaries from input documents, in contrast to executive techniques. Rather than merely copy fragments from the input, abstractive summarization might produce novel words or cover principal information such that the output remains linguistically fluent.
Transformers are a type of neural architecture introduced in a paper by researchers at Google Brain, Googles AI research division. As do all deep neural networks, they contain functions (neurons) arranged in interconnected layers that transmit signals from input data and slowly adjust the synaptic strength (weights) of each connection thats how all AI models extract features and learn to make predictions. But Transformers uniquely have attention. Every output element is connected to every input element, and the weightings between them are calculated dynamically.
The team devised a training task in which whole, and putatively important, sentences within documents were masked. The AI had to fill in the gaps by drawing on web and news articles, including those contained within a new corpus (HugeNews) the researchers compiled.
In experiments, the team selected their best-performing Pegasus model one with 568 million parameters, or variables learned from historical data trained on either 750GB of text extracted from 350 million web pages (Common Crawl) or on HugeNews, which spans 1.5 billion articles totaling 3.8TB collected from news and news-like websites. (The researchers say that in the case of HugeNews, a whitelist of domains ranging from high-quality news publishers to lower-quality sites was used to seed a web-crawling tool.)
Pegasus achieved high linguistic quality in terms of fluency and coherence, according to the researchers, and it didnt require countermeasures to mitigate disfluencies. Moreover, in a low-resource setting with just 100 example articles, it generated summaries at a quality comparable to a model that had been trained on a full data set ranging from 20,000 to 200,000 articles.
Read more here:
Google Brains AI achieves state-of-the-art text summarization performance - VentureBeat
- Classic reasoning systems like Loom and PowerLoom vs. more modern systems based on probalistic networks [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Using Amazon's cloud service for computationally expensive calculations [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Software environments for working on AI projects [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- New version of my NLP toolkit [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Semantic Web: through the back door with HTML and CSS [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Java FastTag part of speech tagger is now released under the LGPL [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Defining AI and Knowledge Engineering [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Great Overview of Knowledge Representation [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Something like Google page rank for semantic web URIs [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- My experiences writing AI software for vehicle control in games and virtual reality systems [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- The URL for this blog has changed [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- I have a new page on Knowledge Management [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- N-GRAM analysis using Ruby [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Good video: Knowledge Representation and the Semantic Web [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Using the PowerLoom reasoning system with JRuby [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Machines Like Us [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- RapidMiner machine learning, data mining, and visualization tool [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- texai.org [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- NLTK: The Natural Language Toolkit [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- My OpenCalais Ruby client library [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Ruby API for accessing Freebase/Metaweb structured data [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Protégé OWL Ontology Editor [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- New version of Numenta software is available [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Very nice: Elsevier IJCAI AI Journal articles now available for free as PDFs [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Verison 2.0 of OpenCyc is available [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- What’s Your Biggest Question about Artificial Intelligence? [Article] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Minimax Search [Knowledge] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Decision Tree [Knowledge] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- More AI Content & Format Preference Poll [Article] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- New Planners Solve Rescue Missions [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Neural Network Learns to Bluff at Poker [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Pushing the Limits of Game AI Technology [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Mining Data for the Netflix Prize [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Interview with Peter Denning on the Principles of Computing [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Decision Making for Medical Support [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Neural Network Creates Music CD [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- jKilavuz - a guide in the polygon soup [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Artificial General Intelligence: Now Is the Time [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Apply AI 2007 Roundtable Report [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- What Would You do With 80 Cores? [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Software Finds Learning Language Child's Play [News] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Artificial Intelligence in Games [Article] [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Artificial Intelligence Resources [Last Updated On: November 8th, 2009] [Originally Added On: November 8th, 2009]
- Alan Turing: Mathematical Biologist? [Last Updated On: April 25th, 2012] [Originally Added On: April 25th, 2012]
- BBC Horizon: The Hunt for AI ( Artificial Intelligence ) - Video [Last Updated On: April 30th, 2012] [Originally Added On: April 30th, 2012]
- Can computers have true artificial intelligence" Masonic handshake" 3rd-April-2012 - Video [Last Updated On: April 30th, 2012] [Originally Added On: April 30th, 2012]
- Kevin B. Korb - Interview - Artificial Intelligence and the Singularity p3 - Video [Last Updated On: April 30th, 2012] [Originally Added On: April 30th, 2012]
- Artificial Intelligence - 6 Month Anniversary - Video [Last Updated On: April 30th, 2012] [Originally Added On: April 30th, 2012]
- Science Breakthroughs [Last Updated On: April 30th, 2012] [Originally Added On: April 30th, 2012]
- Hitman: Blood Money - Part 49 - Stupid Artificial Intelligence! - Video [Last Updated On: April 30th, 2012] [Originally Added On: April 30th, 2012]
- Research Members Turned Off By HAARP Artificial Intelligence - Video [Last Updated On: April 30th, 2012] [Originally Added On: April 30th, 2012]
- Artificial Intelligence Lecture No. 5 - Video [Last Updated On: April 30th, 2012] [Originally Added On: April 30th, 2012]
- The Artificial Intelligence Laboratory, 2012 - Video [Last Updated On: April 30th, 2012] [Originally Added On: April 30th, 2012]
- Charlie Rose - Artificial Intelligence - Video [Last Updated On: April 30th, 2012] [Originally Added On: April 30th, 2012]
- Expert on artificial intelligence to speak at EPIIC Nights dinner [Last Updated On: May 4th, 2012] [Originally Added On: May 4th, 2012]
- Filipino software engineers complete and best thousands on Stanford’s Artificial Intelligence Course [Last Updated On: May 4th, 2012] [Originally Added On: May 4th, 2012]
- Vodafone xone™ Hackathon Challenges Developers and Entrepreneurs to Build a New Generation of Artificial Intelligence ... [Last Updated On: May 4th, 2012] [Originally Added On: May 4th, 2012]
- Rocket Fuel Packages Up CPG Booster [Last Updated On: May 4th, 2012] [Originally Added On: May 4th, 2012]
- 2 Filipinos finishes among top in Stanford’s Artificial Intelligence course [Last Updated On: May 5th, 2012] [Originally Added On: May 5th, 2012]
- Why Your Brain Isn't A Computer [Last Updated On: May 5th, 2012] [Originally Added On: May 5th, 2012]
- 2 Pinoy software engineers complete Stanford's AI course [Last Updated On: May 7th, 2012] [Originally Added On: May 7th, 2012]
- Percipio Media, LLC Proudly Accepts Partnership With MIT's Prestigious Computer Science And Artificial Intelligence ... [Last Updated On: May 10th, 2012] [Originally Added On: May 10th, 2012]
- Google Driverless Car Ok'd by Nevada [Last Updated On: May 10th, 2012] [Originally Added On: May 10th, 2012]
- Moving Beyond the Marketing Funnel: Rocket Fuel and Forrester Research Announce Free Webinar [Last Updated On: May 10th, 2012] [Originally Added On: May 10th, 2012]
- Rocket Fuel Wins 2012 San Francisco Business Times Tech & Innovation Award [Last Updated On: May 13th, 2012] [Originally Added On: May 13th, 2012]
- Internet Week 2012: Rocket Fuel to Speak at OMMA RTB [Last Updated On: May 16th, 2012] [Originally Added On: May 16th, 2012]
- How to Get the Most Out of Your Facebook Ads -- Rocket Fuel's VP of Products, Eshwar Belani, to Lead MarketingProfs ... [Last Updated On: May 16th, 2012] [Originally Added On: May 16th, 2012]
- The Digital Disruptor To Banking Has Just Gone International [Last Updated On: May 16th, 2012] [Originally Added On: May 16th, 2012]
- Moving Beyond the Marketing Funnel: Rocket Fuel Announce Free Webinar Featuring an Independent Research Firm [Last Updated On: May 23rd, 2012] [Originally Added On: May 23rd, 2012]
- MASA Showcases Latest Version of MASA SWORD for Homeland Security Markets [Last Updated On: May 23rd, 2012] [Originally Added On: May 23rd, 2012]
- Bluesky Launches Drones for Aerial Surveying [Last Updated On: May 23rd, 2012] [Originally Added On: May 23rd, 2012]
- Artificial Intelligence: What happened to the hunt for thinking machines? [Last Updated On: May 25th, 2012] [Originally Added On: May 25th, 2012]
- Bubble Robots Move Using Lasers [VIDEO] [Last Updated On: May 25th, 2012] [Originally Added On: May 25th, 2012]
- UHV assistant professors receive $10,000 summer research grants [Last Updated On: May 27th, 2012] [Originally Added On: May 27th, 2012]
- Artificial intelligence: science fiction or simply science? [Last Updated On: May 28th, 2012] [Originally Added On: May 28th, 2012]
- Exetel taps artificial intelligence [Last Updated On: May 29th, 2012] [Originally Added On: May 29th, 2012]
- Software offers brain on the rain [Last Updated On: May 29th, 2012] [Originally Added On: May 29th, 2012]
- New Dean of Science has high hopes for his faculty [Last Updated On: May 30th, 2012] [Originally Added On: May 30th, 2012]
- Cognitive Code Announces "Silvia For Android" App [Last Updated On: May 31st, 2012] [Originally Added On: May 31st, 2012]
- A Rat is Smarter Than Google [Last Updated On: June 5th, 2012] [Originally Added On: June 5th, 2012]