Effortless Bot Training
with the Power of LLM Technology
with the Power of LLM Technology
Speedup the training process for your virtual assistants with a Multi-model NLU Approach to experience maximum efficiency.
Virtual assistants built on the Kore.ai XO Platform use multiple NLU models for training, including Zero-shot, Few-shot and Curated Models. These approaches accelerate the Virtual Assistant’s development with minimal to no training while still providing the best intent-recognition.
The core of the NLP lies with multiple engines — machine learning, fundamental meaning and knowledge graph. These three engines work together in tandem to efficiently understand the user queries and respond with the best answers.
Eliminate training needs and give more power to developers with zero-shot training. The latest model integrates with Open AI and uses a pre-trained language model combined with a logic learning machine to identify user intents accurately. The OpenAI LLM & Generative AI models identify the intents accurately by comparing user utterances.
The Few-Shots model allows you to train your virtual assistants using the task names and a few training utterances. This model uses Kore.ai custom NLU models that are pre-trained with large datasets to identify intents using semantic similarity. This model is secure as it does not share any data externally and needs no additional enablement or costs. You can also train the models for better efficiency.
The XO Platform uses a unique Natural Language Processing strategy that combines Machine Learning, Fundamental Meaning and Knowledge Graph engines to achieve the highest intent recognition with minimal training.
With this strategy, virtual assistants developed on the Kore.ai XO Platform will understand multiple intents, traits, idioms and other language nuances.
Machine Learning allows you to train your Intents/Tasks with sample data and learns from them using Deep Neural Network models that accurately predict more varied inputs from the user. Ex: “I want to pay,” can be a sample utterance for the intent as Pay Bill.
Named Entity Recognition model allows you to mark entities from the user utterances and train the assistant to identify them accurately. System entities like Date, Number, Currency, Country etc are identified out of the box. NER training helps even in predicting the Custom or Domain-driven entities like Account Types, Card Type etc. Kore.ai allows a VA developer to choose the ML model relevant for their Data by providing the choice of cutting edge DNN based models like LSTM, CNN, KAEN. We can integrate any 3rd party ML engine too if required. Also, configure the agent to auto-learn from the successfully executed tasks.
The Knowledge Graph engine supports a large set of intents in the form of questions. This allows you to import large volumes of information quickly, group and annotate the key terms, add synonyms, and provide alternate queries. There is also the option to build a hierarchy.
Alternatively, you can download the Ontology generator from Github to automatically generate a knowledge graph for your virtual assistant. The Knowledge Extraction engine allows information to be extracted from unstructured documents and to understand queries.
Use the Fundamental Meaning engine to train idiomatic or command-like sentences. The engine uses a semantic approach to understand grammar and language nuances to empower virtual assistants to associate synonyms with task names. This mapping improves intent recognition rates and when combined with patterns, can be used to train VAs to recognize idiomatic expressions.
Traits
Traits are specific entities, attributes, or details that users express in their conversations. It is common for users to provide background information in natural conversations while describing a scenario. TheTraits feature uses this background information to identify the user’s intent and drive the conversational flow accordingly.
For instance, if “I am looking for a low-cost option to London” is the user’s utterance then using the Traits feature,the virtual assistant will be able to identify the intent as flight booking.
Guided Training
Virtual assistants perform best when you train them with accurate and adequate data. To help you provide superior training, the XO Platform provides proactive validations. It guides you to improve the VAs’ performance by constantly validating the NLU model and alerts you with errors and warning notifications.
The update focuses on validations related to the intent training with the ML & FM Engines for untrained intents, inadequate training, utterance does not qualify any intent, utterance predicts an incorrect intent, utterance predicts the expected intent with low confidence, incorrect intent patterns, short training utterances, incorrect entity annotations and more.
Learn how Kore.ai products and solutions can drive ROI, reduce expenses and increase revenue.