Semantics: next step in KM

The message from those giants was surprisingly consistent. In 2013, organizations worldwide need better access to information and "better outcomes."

After several sessions about the European Community's efforts to improve search and retrieval, I spoke with Antonio Valderrábanos, the founder of Bitext, a semantic technology company based in Spain. Bitext provides business-to-business multilingual semantic technologies. Valderrábanos suggests that Bitext delivers tagging accuracy that is among the best in the world. Its system supports text analytics and social customer relationship management.

Like other companies in that sector, Bitext's services are available through two different channels: the Bitext API, which provides a Web service for third-party developers, and Bitext consulting, which includes customization services for applications such as business intelligence or contextual advertising.

Growing interest

When I asked Valderrábanos about applications for semantic technology, he responded: "The interest in semantic technology is growing. The applications range from search engines and NL interfaces (like virtual assistants) to text analytics solutions for social customer relationship management, social media monitoring, enterprise feedback management, voice of the customer and business intelligence. In both North America and Europe, consumerization brings us closer to the user, and this is very good news. Learning what it is that users want is an important information asset. Consumerization can help us identify applications that users want, like review sites, and design semantic enhancements for those sites. Remember we complement third-party applications with NLP functionality. It will be interesting to see which search or text analytics applications get traction."

I have been skeptical of next-generation search technologies. I asked Valderrábanos if semantic technology has made findability easier for business professionals. He said:

"I think mash-ups and more user friendly outputs are a big breakthrough. These approaches centralize access to information, and they will trigger high-value applications. Merging related data is good. However, systems have to be clever enough to keep track of the origin of the information, since this origin provides context. As you know, data from a customer support system is different from data from a business process management system or a legacy repository of unstructured information."

Looking forward

At the CeBIT show, I noted considerable interest in solving the problems of information retrieval. Mobile vendors need to provide specific information with limited screen real estate. Enterprise vendors like IBM, SAP and Oracle emphasized the growing need to provide accurate, integrated answers to user queries.

When asked how Bitext integrates with enterprise systems from the dominant vendors of enterprise solutions, Valderrábanos responded:

"Our approach has to do with flexibility as the main feature of our technology. We have an NLP platform that performs a modular linguistic analysis of any type of text and, as such, we can fine-tune grammars and dictionaries to better handle the output required by our customers. Our solution "snaps in," that is, almost no specialized work-arounds are needed. Plus, we take a personal interest in each of our client's requirements. Our client focus means that we can go beyond canned solutions based on keywords and delve deeply into linguistic structure. In this way, we provide a solution that can detect semantically meaningful information which fits the customer's needs. Remember, we can do so in multiple languages because of our modular approach. When a new language capability is required, we can exchange dictionary and grammars of the languages we support without changing the NLP core engine. In addition, we make our technology available via our API so our customers can try the technology right away and provide feedback for improving coverage and precision."

Valderrábanos described the outlook for semantic technology as follows:

"The most relevant trend we see is the integration of pure search (enhanced with natural language processing functionalities) with text analytics. The idea is that a user can ask a question, for example, for negative opinions on a given product that mention customer service. In this environment, text analytics enriches the indexing phase so the index is not based on isolated words, as usual, but on meaningful expressions (like entities, "New Balance," or concepts, "customer service") and on connections between these expressions ("New Balance improves its customer service"). Being able to query in natural language and select only texts with certain features (for sentiment, category) opens a new era for users exploiting text databases. This trend will be meaningful in different areas like social CRM, where user comments from social media can be connected to customer support function. And in business intelligence, a system will connect classical numeric indicators with user comments coming from the contact center. Business management will not be anymore about numbers, but about text integrated with numbers."

In the last 30 years, there has been much talk about semantic technology. What seems to be unfolding in 2013 is that vendors are providing solutions that address quite specific customer needs. Semantic technology can improve indexing, identify entities and output tags, which can be analyzed by sophisticated numerical recipes. In addition, specific language operations yield useful insights into the emotional freight conveyed by comments.