Starting June 2020 (Summer Release), Salesforce customers who have subscribed to its Einstein Vision & Language services will gain access to Named Entity Recognition (NER). This means that sales reps would now be able to tap the recently-launched Einstein Voice Assistant and Einstein Bots for updating fields in customer relationship management forms.
What is Named Entity Recognition and how does it work?
Communication has always been a huge component of human intelligence. Teaching computers to analyze and process the way human beings naturally speak or write (once transcribed) is known as Natural Language Processing, or NLP.
When human beings communicate through written or spoken language, they are doing many “tasks,” even without realizing it. For instance, we may be analyzing for sentiment, or understanding if someone is asking a question, or judging what the intent is of what someone writes or says.
We need to break down communication into these tasks with an attempt to program computers to interpret natural language. One task is to understand the sentiment of a piece of text, NER is another task.
For instance, if someone sends a chat message that says, “Please change my shipping address to 132 Cloud St, Cumulonimbus, CA 90260,” Einstein Bots make use of NER to understand that “132 Cloud St, Cumulonimbus, CA 90260” is a “Location” entity and to update the “Delivery Address” field accordingly. This helps in automating workflows and streamline the experiences of customers.
In other words, NER can be defined as categorizing words that are similar to how we as children are taught to categorize words as nouns, verbs, or adjectives. Named Entity Recognition helps us identify words in predefined categories like Name, Date, Phone Number, Organization, and Website Address.
How can customers get access to Einstein NER?
Einstein Named Entity Recognition (NER) is the latest addition to the Einstein Vision & Language services that will be generally available in June 2020, the summer release. Einstein Language – NER, like Einstein Intent and Einstein Sentiment, is available for developers through simple REST APIs and via clicks using the AppExchange package for admins.
Presently, a big majority of cloud-hosted natural language services already support named entity recognition. Microsoft provides an entity recognition skill within its Cognitive Services suite that helps extract items of different types from text. Amazon Comprehend leverages artificial intelligence to glean insights from and spot relationships in text, and the natural language API of Google Cloud can handle a range of entity and entity sentiment analysis tasks.