AI Case Study
Talla plans to enhance knowledge management within organisations with a custom search engine and automatically tagging and summarising documents
Talla has launched a knowledge management AI platform which has a custom search engine to search through documents. The platform also uses natural language processing and machine learning to summarise documents and tag them. The tagging improves over time from user search results. It will also report topics that are not updated or lacking details.
Software And It Services
"Talla acts as a digital assistant that helps automate the knowledge management process by adapting to the needs of each team.
Talla does the following:
Automatically validating information: With Talla, you can say goodbye to stale, duplicate, and scattered content. Talla takes care of keeping your company’s information updated, relevant, and accessible. By validating information, Talla gives users information relevant to them based who they are and what they’ve done in the past.
Dynamically requesting content from users: Eliminate information silos and knowledge gaps. Talla helps you organize your content and manages content requests from users.
Tagging and analyzing content for better organization: Access information even faster. Talla extracts relevant content snippets from knowledge base pages to provide fast access to information.
Talla gives you the power to integrate everything with your chat platform. Employees can simply send Talla a message via Slack, MS Teams, or TallaChat to get instant access to the information they’re looking for."
POC; Results not yet available
"Semantic matching, neural machine translation, active learning, and topic modeling. Users train Talla by creating and annotating knowledge base documents. Talla continually learns what’s relevant and important to deliver a better experience over time."
"Talla's internal search engine is "aware" of the structure of your knowledge base content, so it can distinguish between titles, section headers, and body content. If you have a master policy document (as denoted by a title), with a section on parking policies (as denoted by a section header), and a paragraph that addresses the Boston office's parking policy (as denoted by body content), Talla's search engine would jump to the correct paragraph of the document when you search a phrase like "Boston parking policy".
Moreover, Talla's search engine would "learn" over time if the overall document, and the specific paragraph it suggested, were the best result for that query, and adjust its results accordingly.
In a more advanced scenario, you could simply search "parking policy" and, given your user profile in Talla, the search engine would already know you work in the Boston office and give you the Boston policy excerpt without you even including the word "Boston" in your search query. The Talla A.I. would learn whether this technique works for you, and works in general, and over time would adapt its search behavior to be more useful."
"Information changes so quickly, and keeping it updated in company’s knowledge base becomes an enormous task. This often results in them becoming document graveyards; content goes stale, gets duplicated, or is difficult to find."