Enrich digital experiences by introducing chatbots that can hold smart, human-like conversations with your customers and employees. Use our proprietary, state-of-the-art, Natural Language Processing capabilities that enable chatbots to understand, remember and learn from the information gathered during each interaction and act accordingly.
Interprets accurately with fewer false positives
Resolves development gaps faster
Requires less training data to be NL capable
Repurposes training data
Maintain the context of user’s request throughout a dialogue or session
Extract and Store actions taken, data provided, and information pulled from systems the bot can use
Customize how contextual data is stored at the session
Use Pre-trained NLP models to perfect your chatbot’s NLP
In order for your chatbot to break down a sentence to get to the meaning of it, we have to consider the essential parts of the sentence. One useful way that the wider community of researchers into Artificial Intelligence do this is to distinguish between Entities and Intents.
An Entity in a sentence is an object in the real world that can be named. Our NLP models are excellent at identifying Entities and can do so with near-human accuracy. Through our NLP engine, the bot identifies words from a user’s utterance to ensure all available fields match the task at hand or collects additional field data if needed. The goal of entity extraction is to fill any holes needed to complete a task, while ignoring unneeded details. It’s a subtractive process where the chatbot gets just the necessary info: whether provided all at once by the user or through a guided conversation with the chatbot.
Intent in a sentence is the purpose or goal of the statement. In a sentence of the type, ‘I would like to book two tickets for the new Spielberg film’ it is easy to identify the Intent, namely “to make a booking”. Many sentences, however, do not have clear Intent. So it is more challenging for a chatbot to recognize Intent but again, our NLP models are very effective at it. The goal of intent recognition isn’t just to match an utterance with a task, it’s to match an utterance with its correctly intended task. We do this by matching verbs and nouns with as many obvious and non-obvious synonyms as possible.
To make NLP work for particular goals, users will need to define all the types of Entities and Intents that the user wants the bot to recognise. In other words, users will create several NLP models, one for every Entity or Intent you need your chatbot to be able to identify. Users can build as many NLP models on our platform as they need. So, for example, you might build an NLP Intent model so that the bot can listen out for whether the user wishes to make a purchase. And an Entity model which recognises locations and another that recognises ages. Your chatbots can then utilise all three to offer the user a purchase from a selection that takes into account the age and location of the customer.
On our platform, users don’t need to build a new NLP model for each new bot that they create. All of the chatbots created will have the option of accessing all of the NLP models that a user has trained.
To develop an NLP model over time, so that it becomes more and more accurate at solving the task users want to address, users will want the chatbot to learn, especially from its mistakes. Machine Learning is a hot topic in the search for true Artificial Intelligence. Our models embody Machine Learning in the sense that on the basis of having provided example sentences and their outcomes, the model will make decisions about new sentences it encounters.
Our platform also offers what is sometimes termed supervised Machine Learning. In the light of data from your conversations, you can spot where the chatbot needs more training and input the problematic sentences you have identified, along with the correct result that the bot should arrive at when examining the sentence. This supervised Machine Learning will result in a higher rate of success for the next round of unsupervised Machine Learning. This process of cycling between your supervision and independently carrying out the assessment of sentences will eventually result in a highly refined and successful model.
The great news is that we provide pre-trained NLP models.
These are state-of-the-art Entity-seeking models, which have been trained against massive datasets of sentences.
So, for example, our NLP model Negative Entities is ideal for recognizing frustration in the user. You can deploy this model in minutes and your chatbot will be able to analyze the conversation and say sentences like, ‘I see you are not enjoying this conversation, would you like to talk to a human agent instead?’ And then the chatbot can call the agent by SMS or email if the user wishes.