Word Embedding Captures Semantic Relationships
November 10, 2016
The article on O’Reilly titled Capturing Semantic Meanings Using Deep Learning explores word embedding in natural language processing. NLP systems typically encode word strings, but word embedding offers a more complex approach that emphasizes relationships and similarities between words by treating them as vectors. The article posits,
For example, let’s take the words woman, man, queen, and king. We can get their vector representations and use basic algebraic operations to find semantic similarities. Measuring similarity between vectors is possible using measures such as cosine similarity. So, when we subtract the vector of the word man from the vector of the word woman, then its cosine distance would be close to the distance between the word queen minus the word king (see Figure 1).
The article investigates the various neural network models that prevent the expense of working with large data. Word2Vec, CBOW, and continuous skip-gram are touted as models and the article goes into great technical detail about the entire process. The final result is that the vectors understand the semantic relationship between the words in the example. Why does this approach to NLP matter? A few applications include predicting future business applications, sentiment analysis, and semantic image searches.
Chelsea Kerwin, November 10, 2016
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
Digging for a Direction of Alphabet Google
April 21, 2016
Is Google trying to emulate BAE System‘s NetReveal, IBM i2, and systems from Palantir? Looking back at an older article from Search Engine Watch, How the Semantic Web Changes Everything for Search may provide insight. Then, Knowledge Graph had launched, and along with it came a wave of communications generating buzz about a new era of search moving from string-based queries to a semantic approach, organizing by “things”. The write-up explains,
“The cornerstone of any march to a semantic future is the organization of data and in recent years Google has worked hard in the acquisition space to help ensure that they have both the structure and the data in place to begin creating “entities”. In buying Wavii, a natural language processing business, and Waze, a business with reams of data on local traffic and by plugging into the CIA World Factbook, Freebase and Wikipedia and other information sources, Google has begun delivering in-search info on people, places and things.”
This article mentioned Knowledge Graph’s implication for Google to deliver strengthened and more relevant advertising with this semantic approach. Even today, we see the Alphabet Google thing continuing to shift from search to other interesting information access functions in order to sell ads.
Megan Feil, April 21, 2016
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
Celebros Launches Natural Language Processing Ecommerce Extension with Seven Conversions
March 9, 2016
An e-commerce site search company, Celebros, shared a news release touting their new product. Celebros, First to Launch Natural Language Site Search Extension for Magento 2.0 announces their Semantic Site Search extension for Magento 2.0. Magento 2.0 boasts the largest marketplace of e-commerce extensions in the world. This product, along with other Magento extensions, are designed to help online merchants expand their marketing and e-commerce capabilities. Celebros CMO and President of Global Sales Jeffrey Tower states,
“Celebros is proud to add the new Magento 2 extension to our existing and very successful Magento 1 extension. Celebros will offer the new extension free of charge to our entire Magento client base to ensure an easy, fast and pain-free upgrade while providing free integrations to new Celebros clients world-wide. The new extension encompasses our Natural Language Site Search in seven languages along with eight additional features that include our advanced auto-complete, guided navigation, dynamic landing pages and merchandising engine, product recommendations and more.”
For online retailers, extension products like Celebros may make or break the platforms like Magento 2.0, as these products are what add value and drive e-commerce technologies forward. It is intriguing that the Celebros natural language processing technology offers conversions available in seven languages. We live in an increasingly globalized world.
Megan Feil, March 9, 2016
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
Whitepaper: Plan for Holiday Sales Now
October 16, 2015
Marketing pros and retailers take note: semantic tech firm ntent offers a free whitepaper to help you make the most of the upcoming holiday season, titled “Step-By-Step Guide to Holiday Campaign Planning.” All they want in return are your web address, contact info, and the chance to offer you a subscription to their newsletter, blog, and updates. (That checkbox is kindly deselected by default.) The whitepaper’s description states:
“Halloween candy and costumes are already overflowing on retail stores shelves. You know what that means, don’t you? It’s time for savvy marketers to get serious about their online retail planning for the impending holidays, if they haven’t already started. Why is it so important to take the time to coordinate a solid holiday campaign? Because according to the National Retail Federation [PDF] the holiday season can account for more than 20–40% of a retailer’s annual sales. And if that alone isn’t enough to motivate you, Internet Retailer reported that online retail sales this year are predicted to reach $349.06 billion a 14.2% YoY increase—start planning now to get your piece of the pie! Position your business for online success, more sales and more joy as you head into 2016 using these easy-to-follow, actionable tips!”
The paper includes descriptions of tactics and best practices, as well as a monthly to-do list and a planning worksheet. Founded in 2010, ntent leverages their unique semantic search technology to help clients quickly find the information they need. The company currently has several positions open at their Carlsbad, California, office.
Cynthia Murrell, October 16, 2015
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
Mondeca Has a Sandbox
September 15, 2015
French semantic tech firm Mondeca has their own research arm, Mondeca Labs. Their website seems to be going for a playful, curiosity-fueled vibe. The intro states:
“Mondeca Labs is our sandbox: we try things out to illustrate the potential of Semantic Web technologies and get feedback from the Semantic Web community. Our credibility in the Semantic Web space is built on our contribution to international standards. Here we are always looking for new challenges.”
The page links to details on several interesting projects. One entry we noticed right away is for an inference engine; they say it is “coming soon,” but a mouse click reveals that no info is available past that hopeful declaration. The site does supply specifics about other projects; some notable examples include linked open vocabularies, a SKOS reader, and a temporal search engine. See their home page, above, for more.
Established in 1999, Mondeca has delivered pragmatic semantic solutions to clients in Europe and North America for over 15 years. The firm is based in Paris, France.
Cynthia Murrell, September 15, 2015
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
Want To Know What A Semantic Ecosystem Is
July 8, 2015
Do you want to know what a semantic ecosystem is? The answer is available from TopQuadrant in its article, “Semantic Ecosystem-What’s That About?” According to the article, a semantic ecosystem enables patterns to be discovered, show the relationships between and within data sources, add meaning to raw data artifacts, and dynamically bring information together.
In short, it shows how data and its sources connect with each other and extracts relationships from it.
What follows the brief explanation about what a semantic ecosystem can do is a paragraph about the importance of data, how it takes many forms, etc., etc. Trust me, you have heard it before. It then makes a comparison with a natural ecosystem, i.e. the ones find in nature.
The article continues with this piece:
“As in natural ecosystems, we believe that success in business is based on capability – and the ability to adapt and evolve new capabilities. Semantic ecosystems transform existing diverse information into valuable semantic assets. Key characteristics of a semantic ecosystem are that it is adaptable and evolvable. You can start small – with one or more key business solutions and a few data sources – and the semantic foundation can grow and evolve with you.”
It turns out a semantic ecosystem is just another name for information management. TopQuadrant coined the term to associate with their products and services. Talk about fancy business jargon, but TopQuadrant makes a point about having an information system work so well that it seems natural. When a system works naturally, it is able to intuit needs, interpret patterns, and make educated correlations between data.
Whitney Grace, July 8, 2015
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
Solcara Is The Best! Ra Ra Ra!
June 15, 2015
Thomson-Reuters is a world renowned news syndication, but the company also has its own line of search software called Solcara Federated Search also known as Solcara SolSearch.” In a cheerleading press release, Q-resolve highlights Solcara’s features and benefits: “Solcara Legal Search, Federated Search And Know How.” Solcara allows users to search multiple information resources, including intranets, databases, Knowledge Management, and library and document management systems. It returns accurate results according to the inputted search terms or keywords. In other words, it acts like an RSS feed combined with Google.
Solcara also has a search product specially designed for those in the legal profession and the press release uses a smooth reading product description to sell it:
“Solcara legal Search is as easy to use as your favorite search engine. With just one search you can reference internal documents and approved legal information resources simultaneously without the need for large scale content indexing, downloading or restructuring. What’s more, you can rely on up-to-date content because all searches are carried out in real time.”
The press release also mentions some other tools, case studies, and references the semantic Web. While Solcara does sound like a good product and comes from a reliable new aggregator like Thomson-Reuters, the description and organization of the press release makes it hard to understand all the features and who the target consumer group is. Do they want to sell to the legal profession and only that group or do they want to demonstrate how Solcara can be adapted to all industries that digest huge information amounts? The importance of advertising is focusing the potential buyer’s attention. This one jumps all over the place.
Whitney Grace, June 15, 2015
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
Eric Schmidt On Search Ambition and Attitude at the GOOG
May 20, 2015
The article on Business Insider titled Google’s Former CEO Reveals The Complicated Search Question He Wants Google To Be Able To Answer reports on Eric Schmidt’s speech in Berlin where he mentioned the hurdles Google is yet to overcome. Obviously, Google is an incredibly ambitious company, and should never be satisfied. He spelled out one particular question he would like the search engine to be able to answer,
“Try a query like ‘show me flights under €300 for places where it’s hot in December and I can snorkel,'” Schmidt says. “That’s kind of complicated: Google needs to know about flights under €300; hot destinations in winter; and what places are near the water, with cool fish to see. That’s basically three separate searches that have to be cross-referenced to get to the right answer. Sadly, we can’t solve that for you today. But we’re working on it.”
Schmidt also argued on behalf of Google in regards to the EU investigation into Google possibly favoring its own results rather than a fair spread of companies. Schmidt claimed that Google is most interested in simplifying search for users, rather than obliging users to click around. Since Google search is admittedly ad-oriented, Schmidt’s position seems to be at least semi-accurate.
Chelsea Kerwin, May 20 , 2014
Stephen E Arnold, Publisher of CyberOSINT at www.xenky.com
Cerebrant Discovery Platform from Content Analyst
May 6, 2015
A new content analysis platform boasts the ability to find “non-obvious” relationships within unstructured data, we learn from a write-up hosted at PRWeb, “Content Analyst Announces Cerebrant, a Revolutionary SaaS Discovery Platform to Provide Rapid Insight into Big Content.” The press release explains what makes Cerebrant special:
“Users can identify and select disparate collections of public and premium unstructured content such as scientific research papers, industry reports, syndicated research, news, Wikipedia and other internal and external repositories.
“Unlike alternative solutions, Cerebrant is not dependent upon Boolean search strings, exhaustive taxonomies, or word libraries since it leverages the power of the company’s proprietary Latent Semantic Indexing (LSI)-based learning engine. Users simply take a selection of text ranging from a short phrase, sentence, paragraph, or entire document and Cerebrant identifies and ranks the most conceptually related documents, articles and terms across the selected content sets ranging from tens of thousands to millions of text items.”
We’re told that Cerebrant is based on the company’s prominent CAAT machine learning engine. The write-up also notes that the platform is cloud-based, making it easy to implement and use. Content Analyst launched in 2004, and is based in Reston, Virginia, near Washington, DC. They also happen to be hiring, in case anyone here is interested.
Cynthia Murrell, May 6, 2015
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
Continued Growth and Success at Syl Semantics
May 5, 2015
The article on Yahoo New Zealand titled Syl Semantics Raises New Capital and Appoints New Directors begins by naming the two freshly-minted non-executive directors, Murray Nash and Gene Turner. This is the result of successful capital raising to the tune of a million dollars for the Wellington-based company. Syl Semantics will continue to focus on growing the company with the assistance of the new directors. The article explains,
“Murray Nash is Managing Director of Zusammen, an advisory firm specialising in strategy, finance and capital markets, risk management, and public policy. In 2013 Murray was manager of the Establishment Unit and subsequently the acting Chief Executive of Callaghan Innovation. Murray has been a senior manager in three financial risk management start-ups in New York – supplying technology solutions to global leaders in banking, insurance, asset management and prudential supervision. He has a MComm (Finance) from the University of Auckland.”
Gene Turner’s background is in law and banking. Syl Semantics was created in 2008 and has grown steadily since then, releasing Syl Search in 2011 with great success. Syl Semantics is focused on what they term “Information Intelligence” or the “ability to access and extract value, meaning and learning from information.” James Fowler, the Director of Sales and Marketing, spoke to the ambition and perseverance of the company, which hopes to gain more of a foothold in New Zealand and Australian markets.
Chelsea Kerwin, May 5, 2014
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
-
- Subscribe to Beyond Search
Feature archive
News archive
-
