Follow Along

RSS Feed Join Us on Twitter On Facebook

Get Engaged


Related Reading

Our Sponsors


Join Us

Newsfeeds from around the industry
Google Research Blog
The latest news on Google Research.

  • Teaching machines to read between the lines (and a new corpus with entity salience annotations)
    Posted by Dan Gillick, Research Scientist, and Dave Orr, Product Manager

    Language understanding systems are largely trained on freely available data, such as the Penn Treebank, perhaps the most widely used linguistic resource ever created. We have previously released lots of linguistic data ourselves, to contribute to the language understanding community as well as encourage further research into these areas.

    Now, we’re releasing a new dataset, based on another great resource: the New York Times Annotated Corpus, a set of 1.8 million articles spanning 20 years. 600,000 articles in the NYTimes Corpus have hand-written summaries, and more than 1.5 million of them are tagged with people, places, and organizations mentioned in the article. The Times encourages use of the metadata for all kinds of things, and has set up a forum to discuss related research.

    We recently used this corpus to study a topic called “entity salience”. To understand salience, consider: how do you know what a news article or a web page is about? Reading comes pretty easily to people -- we can quickly identify the places or things or people most central to a piece of text. But how might we teach a machine to perform this same task? This problem is a key step towards being able to read and understand an article.

    One way to approach the problem is to look for words that appear more often than their ordinary rates. For example, if you see the word “coach” 5 times in a 581 word article, and compare that to the usual frequency of “coach” -- more like 5 in 330,000 words -- you have reason to suspect the article has something to do with coaching. The term “basketball” is even more extreme, appearing 150,000 times more often than usual. This is the idea of the famous TFIDF, long used to index web pages.
    Congratulations to Becky Hammon, first female NBA coach! Image via Wikipedia.
    Term ratios are a start, but we can do better. Search indexing these days is much more involved, using for example the distances between pairs of words on a page to capture their relatedness. Now, with the Knowledge Graph, we are beginning to think in terms of entities and relations rather than keywords. “Basketball” is more than a string of characters; it is a reference to something in the real word which we already already know quite a bit about.

    Background information about entities ought to help us decide which of them are most salient. After all, an article’s author assumes her readers have some general understanding of the world, and probably a bit about sports too. Using background knowledge, we might be able to infer that the WNBA is a salient entity in the Becky Hammon article even though it only appears once.

    To encourage research on leveraging background information, we are releasing a large dataset of annotations to accompany the New York Times Annotated Corpus, including resolved Freebase entity IDs and labels indicating which entities are salient. The salience annotations are determined by automatically aligning entities in the document with entities in accompanying human-written abstracts. Details of the salience annotations and some baseline results are described in our recent paper: A New Entity Salience Task with Millions of Training Examples (Jesse Dunietz and Dan Gillick).

    Since our entity resolver works better for named entities like WNBA than for nominals like “coach” (this is the notoriously difficult word sense disambiguation problem, which we’ve previously touched on), the annotations are limited to names.

    Below is sample output for a document. The first line contains the NYT document ID and the headline; each subsequent line includes an entity index, an indicator for salience, the mention count for this entity in the document as determined by our coreference system, the text of the first mention of the entity, the byte offsets (start and end) for the first mention of the entity, and the resolved Freebase MID.
    Features like mention count and document positioning give reasonable salience predictions. But because they only describe what’s explicitly in the document, we expect a system that uses background information to expose what’s implicit could give better results.

    Download the data directly from Google Drive, or visit the project home page with more information at our Google Code site. We look forward to seeing what you come up with!

  • Google Research Awards: Summer 2014
    posted by Maggie Johnson, Director of Education and University Relations

    We have just completed another round of the Google Research Awards, our biannual open call for proposals on computer science-related topics including systems, machine perception, structured data, robotics, and mobile. Our grants cover tuition for a graduate student and provide both faculty and students the opportunity to work directly with Google researchers and engineers.

    This round we received 722 proposals, an increase of 5% over last round, covering 44 countries on 6 continents. After expert reviews and committee discussions, we decided to fund 110 projects. The subject areas that received the highest level of support were systems, human-computer interaction, mobile, and machine perception, with 22% of the funding awarded to universities outside the U.S.

    We introduced three new topics this round, representing important new research areas for Google. Computational neuroscience looks at the information processing properties of the brain and nervous system. One funded proposal will study scene recognition in this context. A second new area is physical interactions with devices. With the introduction of new paradigms such as Google Glass, we can study how such devices expand our processing capabilities. The third new area is online learning at scale, which covers topics such as teacher-student interaction at scale, data-driven adaptive learning, and innovative assessment methods.

    Congratulations to the well-deserving recipients of this round’s awards. If you are interested in applying for the next round (deadline is October 15), please visit our website for more information.

  • Summer Games: Learn to Program
    Posted by Jennifer Vaden Barth, Executive Assistant

    Looking for ways to engage your kids in constructive, meaningful learning? We’ve just launched Blockly Games, our next extension of Blockly, a web­-based graphical programming environment. As part of the generation of new programming environments that provide a more accessible introduction to coding, Blockly Games allows users to create and run programs by arranging blocks with a simple click, drag and drop.
    Blockly Games requires little or no typing, which facilitates young or novice programmers to learn core coding principles in an intuitive way. By minimizing the use of syntax, users are able to focus on the logic and concepts used by computer scientists, progressing at their own pace as they venture through mazes and more advanced arenas.

    Blockly was featured during the 2013 Computer Science Education week where people of all ages tried programming for the first time. Blockly is universally accessible with translations for a number of languages, including German, Vietnamese, Russian and even Klingon.

    We encourage you and your child to explore Blockly Games, where novice programmers of any age begin to learn together. With Blockly Games, the whole family can learn and master basic computer science concepts.

  • Doing Data Science with coLaboratory
    Posted by Kayur Patel, Kester Tong, Mark Sandler, and Corinna Cortes, Google Research

    Building products and making decisions based on data is at the core of what we do at Google. Increasingly common among fields such as journalism and government, this data-driven mindset is changing the way traditionally non-technical organizations do work. In order to bring this approach to even more fields, Google Research is excited to be a partner in the coLaboratory project, a new tool for data science and analysis, designed to make collaborating on data easier.

    Created by Google Research, Matthew Turk (creator of the yt visualization package), and the IPython/Jupyter development team, coLaboratory merges successful open source products with Google technologies, enabling multiple people to collaborate directly through simultaneous access and analysis of data. This provides a big improvement over ad-hoc workflows involving emailing documents back and forth.

    Setting up an environment for collaborative data analysis can be a hurdle, as requirements vary among different machines and operating systems, and installation errors can be cryptic. The coLaboratory Chrome App addresses this hurdle. One-click installs coLaboratory, IPython, and a large set of popular scientific python libraries (with more on the way). Furthermore, because we use Portable Native Client (PNaCl), coLaboratory runs at native speeds and is secure, allowing new users to start working with IPython faster than ever.

    In addition to ease of installation, coLaboratory enables collaboration between people with different skill sets. One example of this would be interactions between programmers who write complex logic in code and non-programmers who are more familiar with GUIs. As shown below, a programmer writes code (step 1) and then annotates that code with simple markup to create an interactive form (step 2). The programmer can then hide the complexity of code to show only the form (step 3), which allows a non-programmer to re-run the code by changing the slider and dropdowns in the form (step 4). This interaction allows programmers to write complex logic in code and allows non-programmers to manipulate that logic through simple GUI hooks.
    For more information about this project please see our talks on collaborative data science and zero dependency python. In addition to our external partners in the coLaboratory project, we would like to thank everyone at Google who contributed: the Chromium Native Client team, the Google Drive team, the Open Source team, and the Security team.

  • Facilitating Genomics Research with Google Cloud Platform
    Posted by Paul C. Boutros, Ontario Institute for Cancer Research, Josh Stuart, UC Santa Cruz, Adam Margolin, Oregon Health & Science University; Nicole Deflaux and Jonathan Bingham, Google Cloud Platform and Google Genomics

    The understanding of the origin and progression of cancer remains in its infancy. However, due to rapid advances in the ability to accurately read and identify (i.e. sequence) the DNA of cancerous cells, the knowledge in this field is growing rapidly. Several comprehensive sequencing studies have shown that alterations of single base pairs within the DNA, known as Single Nucleotide Variants (SNVs), or duplications, deletions and rearrangements of larger segments of the genome, known as Structural Variations (SVs), are the primary causes of cancer and can influence what drugs will be effective against an individual tumor.

    However, one of the major roadblocks hampering progress is the availability of accurate methods for interpreting genome sequence data. Due to the sheer volume of genomics data (the entire genome of just one person produces more than 100 gigabytes of raw data!), the ability to precisely localize a genomic alteration (SNV or SV) and resolve its association with cancer remains a considerable research challenge. Furthermore, preliminary benchmark studies conducted by the International Cancer Genome Consortium (ICGC) and The Cancer Genome Atlas (TCGA) have discovered that different mutation calling software run on the same data can result in detection of different sets of mutations. Clearly, optimization and standardization of mutation detection methods is a prerequisite for realizing personalized medicine applications based on a patient’s own genome.

    The ICGC and TCGA are working to address this issue through an open community-based collaborative competition, run in conjunction with leading research institutions: the Ontario Institute for Cancer Research, University of California Santa Cruz, Sage Bionetworks, IBM-DREAM, and Oregon Health and Sciences University. Together, they are running the DREAM Somatic Mutation Calling Challenge, in which researchers from across the world “compete” to find the most accurate SNV and SV detection algorithms. By creating a living benchmark for mutation detection, the DREAM Challenge aims to improve standard methods for identifying cancer-associated mutations and rearrangements in tumor and normal samples from whole-genome sequencing data.

    Given Google’s recent partnership with the Global Alliance for Genomics and Health, we are excited to provide cloud computing resources on Google Cloud Platform for competitors in the DREAM Challenge, enabling scientists who do not have ready access to large local computer clusters to participate with open access to contest data as well as credits that can be used for Google Compute Engine virtual machines. By leveraging the power of cloud technologies for genomics computing, contestants have access to powerful computational resources and a platform that allows the sharing of data. We hope to democratize research, foster the open access of data, and spur collaboration.

    In addition to the core Google Cloud Platform infrastructure, the Google Genomics team has implemented a simple web-based API to store, process, explore, and share genomic data at scale. We have made the Challenge datasets available through the Google Genomics API. The challenge includes both simulated tumor data for which the correct answers are known and real tumor data for which the correct answers are not known.
    Genomics API Browser showing a particular cancer variant position (highlighted) in dataset in silico #1 that was missed by many challenge participants.
    Although submissions for the simulated data can be scored immediately, the winners on the real tumor data will not immediately be known when the challenge closes. This is a consequence of the fact that current DNA sequencing technology does not provide 100% accurate data, which adds to the complexity of the problem these algorithms are attempting to tackle. Therefore, to identify the winners, researchers must turn to alternative laboratory technologies to verify if a particular mutation that was found in sequencing data is actually (or likely) to be true. As such, additional data will be collected after the Challenge is complete in order to determine the winner. The organizers will re-sequence DNA from the cells of the real tumor using an independent sequencing technology (Ion Torrent), specifically examining regions overlapping the positions of the cancer mutations submitted by the contest participants.

    As an analogy, a "scratched magnifying glass" is used to examine the genome the first time around. The second time around, a "stronger magnifying glass with scratches in different places" is used to look at the specific locations in the genome reported by the challenge participants. By combining the data collected by those two different "magnifying glasses", and then comparing that against the cancer mutations submitted by the contest participants, the winner will then be determined.

    We believe we are at the beginning of a transformation in medicine and basic research, driven by advances in genome sequencing and computing at scale. With the DREAM Challenge, we are all excited to be part of bringing researchers around the world to focus on this particular cancer research problem. To learn more about how to participate in the challenge register here.

All the Latest

Getting Around the Site

Home - all the latest on SNC
SEO - our collection of SEO articles
Technical SEO - for the geeks
Latest News - latest news in search
Analytics - measure up and convert
RSS Rack - feeds from around the industry
Search - looking for something specific?
Authors - Author Login
SEO Training - Our sister site
Contact Us - get in touch with SNC

What's New?

All content and images copyright Search News Central 2014
SNC is a Verve Developments production, the Forensic SEO Specialists- where Gypsies roam.