Using Google Search Appliance (GSA) Metadata Feed to implement Natural Language Search

The Google Search Appliance (GSA) is an excellent standard for enterprise search and is very popular in the market, since it is an easy solution to deploy as a search engine for a website.

Nevertheless, the GSA bases its searches on keywords and not on the meaning of the users’ questions, and this means that the results obtained are often not relevant to the question posed.

Presenting irrelevant results to the users of our website has a cost. They get a bad perception of the service offered, which hurts the corporate image, not to mention the amount of potential sales or transactions that we could be losing by lowering our conversion rate. In short, you can’t afford the cost of having your users not find what they are looking for at the very first try.

But there is a way to fix this:

Inbenta has developed a solution that integrates seamlessly with the functionalities of the GSA, called External Metadata Indexing. The solution created by Inbenta allows this GSA functionality to be used to enter metadata with semantic information. The documents are indexed in seamlessly mode that can’t be perceived by users or content editors.

These metadata contain additional semantic information which makes the documents easier to find with the semantic search extensions of Inbenta.

For example, for a document titled “Where can I view my annual statement?”, Inbenta would create a feed like this, which would also allow user questions such as “find yearly report” to be understood:

This XML feed is created thanks to the powerful natural language processing engine of Inbenta. This process results in combining the advantages of the GSA (robustness, presence on the market and ability to index large amounts of documents) with the advantages of natural language search: more relevant results, the possibility of finding documents without needing to use the exact words those documents use, and the possibility of doing searches based on the overall meaning of the phrase and not on the keywords used, i.e., interacting with the search engine in a more natural way, as though we were talking to a human.

The clients that have incorporated this solution from Inbenta have improved their search engine clickthrough by 300%, meaning there are more users clicking on results that are much more pertinent, thanks to this innovative solution offered by Inbenta.

Thus, with the Inbenta Semantic Connector, you will be able to:

• increase your conversion rate
• reduce the cost of your customer service
• get very important information about your users

You can check out all the information on this product here.

Inbenta and Multiplica Establish Global Partnership

Multiplica, an online consulting firm which combines persuasion and usability in a new concept, “persuadability”, and which specializes in conversion rates, and Inbenta, a leader in Natural Language Processing and Semantic Search, have signed a global partnership agreement to work together to help clients increase online conversion rates and customer satisfaction.

With offices in 8 cities and 6 countries, Multiplica will use Inbenta’s technologies in several projects related to “online persuasion”, a concept created by Multiplica intended to increase usability, user satisfaction and online conversion rates. At the same time, Inbenta and its customers will benefit from Multiplica’s experience in online implementation to get their semantic search applications to reach the next level of efficiency.

According to David Boronat, CEO of Multiplica, “This alliance is the result of several years of combined effort in different projects developed by both companies, which have led to great success for our shared customer base”.

With regard to the evolution of online persuasion, Inbenta CEO Jordi Torras said, “This partnership is the result of bringing together the best of two worlds: the knowledge of Multiplica after years of working on conversion, and Inbenta’s technology that makes website searches a much more human-like experience.”

Instant Answers for Inbenta Email Management

Monday, 16 January 2012 10:20 Instant Answers for Inbenta Email Management
Inbenta’s Email and Ticketing System allows companies to deal with large volumes of customer emails and online forms quickly and effectively.

These online forms allow users to enter their question or concern without actually having to use an Email client software. But often, an existent knowledge base could solve the user’s problem without even having to send the Email.

That’s why Inbenta presents “Instant Answers” for our Email management system, it allows users to intelligently find the information they need using our Natural Language platform even before an Email is sent, in real time, while the Email is being typed.

Whenever the customer is not finding a satisfactory answer, or the existing answers are not solving his/her problem, an actual mail is sent, and ticket is registred in Inbenta’s high-performance ticketing system.

Check out how Instant Answers works in this video.

 

Inbenta improves the memory and detection of context in the dialogs of its 5th generation Virtual Assistants

As part of our never-ending goal to improve user satisfaction, Inbenta has completely redesigned the functionality of cognitive retention, memory and detection of context in interactions between the users and the virtual assistants. This new feature allows our Assistants to be able to remember parts of the conversation had with the user, resulting in more personalized searches and an easier discussion.

The Virtual Assistant of Iberia, the leading company in the airline sector, is able to remember the user’s name, giving the consultations a custom-made feel that increases user confidence in the obtained results and, therefore, in the company.

ASSISTANT: Hello, how can I help you?

USER: Hi! My name is Peter.

ASSISTANT: Hi Peter! It’s great to talk to you,what can I do for you?

Moreover, it has also the memory feature in flight searches in order to optimize interaction with the users. Our Assistant is able to remember the location of the user in such a way that it doesn’t keep asking about it every time they search for this type of information.

USER: flights to Nice

ASSISTANT: You would like to go to Nice which origin?

USER: from Barcelona

ASSISTANT: You would like to fly from Barcelona to Nice: Offers to fly from Barcelona to Rome

USER: and if I want to travel to London?

ASSISTANT: You would like to fly from Barcelona to London: Offers to fly from Barcelona to London

Notice that our linguistic analysis is able to distinguish the city of Nice from the adjective “nice”, thanks to our disambiguation modules that can choose between the most suitable meaning of a polisemous word depending on its context of appearance.

Using Natural Language Search on Twitter Timeline

Using Semantic Search and Natural Language processing technologies on websites has already proven to be a great success in many industries, countries and languages.

The rationale behind it and how a ROI is obtained is easy to understand:

• conversion rate is higher: as users find what they are looking for using their own words, not the author’s words, they will find the product or service the website is offering much faster.

• customer support costs are lower: when users can easily find solutions for their concerns online, they simply won’t contact the call center, nor will they send e-mails for issues that are already solved on the web.

Let’s take the airline industry, where by using Natural Language Search, we should easily be able to find answers like these ones:

Q: can I bring my dobermann onboard

A: I’ve found information about Carriage of domestic pets

Q: do you serve vegetarian food in the plane

A: I’ve found information about Special on-board meals

Q: can I buy a ticket for somebody else

A: How can I buy a ticket for another person?

Once the appropriate knowledge base has been put in place, and the right Semantic Search Engine is made available to the users, the whole website is transformed in a real online customer support portal.

However, not all the questions are easily found in most of the knowledge bases. Let’s take these examples:

• is the strike affecting flights to Paris?

• are there volcano ashes on Madrid airport?

• open job opportunities

What do these questions have in common? All of them refer to issues that are tied to real-time events.

Having a knowledge base, or even a website, permanently updated with these issues is simply impractical.

Yet, most companies are offering valuable information related to real-time events through Twitter, which provides the flexibility to basically “broadcast” valuable last-minute information in real-time, without the hassle of having to update the company’s website, which is a process that may take hours (often days) to take effect.

Let’s take a look at these tweets that have been recently published:

• The list of long-haul flights affected by the SEPLA pilots’ union strike on Jan. 9 & 11 is available at http://ow.ly/8gGPJ.

• Good morning! The volcanic ash cloud is still over Spain. Right now 8 airports are closed

• Iberia Express Opens Pilot Recruitment Process http://ow.ly/87pNa #IbExpress #Job #Employment

This is valuable information that any passenger about to fly would be interested in knowing indeed. Yet, to have this information, users just need to follow that airline Twitter timeline and pay attention to what is going on.

But, what if I miss the tweet that was relevant to me? What if I am not following that company on Twitter? What if I don’t even have a Twitter account? I would simply miss this information.

The solution is basically to consider that the company’s Twitter Timeline is actually an intrinsic part of the the knowledge base, and the natural language search has a key role here.

By doing so, questions about real-time events could still be answered, online, using the current company website, by feeding the knowledge base with all this valuable information.

Consider now the following question/answer dialog:

Q: is the strike affecting flights to Paris?

A: The list of long-haul flights affected by the SEPLA pilots’ union strike on Jan. 9 & 11 is available at http://ow.ly/8gGPJ. /1 (source: Twitter Timeline)

Q: are there volcano ashes on Madrid airport?

A: Good morning! The volcanic ash cloud is still over Spain. Right now 8 airports are closed (source: Twitter Timeline)

Q: open job opportunities

A: Iberia Express Opens Pilot Recruitment Process http://ow.ly/87pNa #IbExpress #Job #Employment (source: Twitter Timeline)

The answers are absolutely relevant. There are no identical words between the question and the answer, but the meaning is very similar. This is thanks to the magic behind Natural Language Processing and Semantic Search.

Besides, implementing this feature is easy. The only requirements are:

• Reading the Twitter Timeline, all informative tweets published by the company and

• Having a semantic search engine armed with a real-time indexer

As companies are looking at social media more and more as an effective way to provide customer service, we believe that real-time indexing and Natural Language processing will have an increased role and importance in many industries that have to deal with real-time events.

Because your customers just can’t wait.

Jordi Torras // CEO Inbenta // http://twitter.com/@jtorras

Inbenta and CodeBaby Partnership will Enhance Web Self-Service Experience

CodeBaby, a company whose award-winning digital characters are shaping the growing online self-service marketplace, today announced its partnership with inbenta, a leader in Natural Language Processing and Semantic Search. Recognizing the expanding market demand for self-service solutions, CodeBaby and inbenta have joined forces to deploy intelligent virtual assistants that increase online conversation rates and customer satisfaction.

The new alliance will deliver technologies through online assistance to web visitors via the CodeBaby Intelligent Virtual Assistant (CIVA) solution which provides digital characters that engage website visitors and seamlessly guides them through the online self-service experience. By driving interaction with the inbenta semantic engine – which incorporates technologies enabling intelligent interactions though its Natural Language Processing solution – visitors dramatically increase their ability to find the information they are seeking online, thereby improving the overall customer experience. This technology reduces operations costs for inbenta customers by diminishing the dependency on customer support professionals.

“A common complaint among web users is that self-service technologies often don’t understand what they’re seeking,” said Dennis McGuire, CodeBaby CEO. “But inbenta’s advanced search capabilities really work to resolve this problem. By integrating CodeBaby’s strengths with inbenta’s technology we will enable a more intelligent website engagement for consumers and thus, better results for our customers.”

In addition to reducing the dependency on customer support, the digital characters serve as brand representatives to influence desired online customer behavior.

Speaking on the evolution of self-service technology, inbenta CEO Jordi Torras said, “This partnership is the result of the best of two technologies: one that humanizes the internet and one that interacts more intuitively with human queries and commands. Through years of determination, inbenta has now created a product that responds to searches as questions or statements, not limiting web users to keywords.”

Read the full article here.

CatalunyaCaixa responds to their clients’ questions with the technology of Inbenta

Inbenta was the company selected by CatalunyaCaixa to implement the latest version of its advanced semantic search engine in its Internet portal.

The solution implemented by CatalunyaCaixa combines the technology of auto-complete and predictive search with the semantic search engine, along with the module of dynamic questions and response assessments. Furthermore, it incorporates the module of campaigns and banners relevant to context in order to boost the user’s access to useful information according to their queries.

“The interest CatalunyaCaixa has in client satisfaction has led them to develop this solution, which provides users the appropriate steps and settles doubts quickly and efficiently”, says Julio Prada, Director of Inbenta. “This project can be taken as an example of the success reached by semantic search engines in this sector, where client satisfaction is paramount”.

In order to complete the search engine of CatalunyaCaixa, Inbenta focused on the concerns of its users, who formulated their questions in different ways which varied according to each individual’s skill and experience.

The search engines that Inbenta puts forth ignore “how” the question was written in order to focus on “what” it means, applying linguistic algorithms. This is how they achieve better results in score and relevancy than traditional search engines, and better results for the user.

See the original article in Spanish here.

Iberia connects its Virtual Assistant to the intelligence of social networks

Tuesday, 13 December 2011 10:08 Iberia connects its Virtual Assistant to the intelligence of social networks
After its merger last January with British Airways shaping the new International Airlines Group (IAG), the company Iberia is the third largest air transportation group in Europe and the sixth largest in the world in revenue, and it comes in first place in the European-Latin American market according to their range of destinations and frequencies.
Iberia has installed the Virtual Assistant created by Inbenta. The ultimate goal of this initiative is to “facilitate browsing by the user and improve the service provided to them, by getting information searches to lead to truly pertinent results”, explains the head of the Technological Development Unit of Iberia.com Assistant Management, Rafael Arroyo.
In the process of increasing its intelligence, we have incorporated our Twitter timeline, in order to take into account, for example, information that may be related to catastrophes, strikes or incidents that could affect the clients.
You can see all the information (in Spanish) here.

UserZoom, the experts in usability, use Inbenta as their website search engine

Usability software maker UserZoom has chosen Inbenta as the search engine for their website (www.userzoom.com).

UserZoom helps companies like PayPal, eBay, and Verizon meet their top usability standards, and Inbenta is enabling them to:

• dramatically increase their website search efficiency

• learn what their customers and prospects want

• increase qualified website visitors using Inbenta’s long-tail and automated SEO tools

Find more about how Inbenta has helped Userzoom at http://www.userzoom.com/news-feed/search-engine-inbenta

Direct Seguros is now using Facebook as an additional customer service channel

After using inbenta’s dynamic FAQ on its website (www.directseguros.es) to answer any question their Internet users may have and build over the time an exhaustive and relevant FAQ, Direct Seguros is now using the same solution but on another channel: Facebook.

Direct Seguros’ Fans can now from Facebook express any doubt or question they may have regarding their offer and services and get instant and relevant answers!

 

The FAQ is exactly the same than the one available on the web site directseguros.es : it’s the same resource that can be now used and improved by the 2 different channels!

Our solution on Facebook allows you to :

• Answer immediately your Fan’s questions without leaving Facebook

• Reduce the number of recurrent and negative posts on your wall

• Redirect them efficiently to your website

• Build an exhaustive FAQ based on the real needs expressed by your Fans