Google Launched Semantic Reactor for natural language understanding experimentation
Google launched Semantic Reactor for natural language understanding experimentation. Researchers describes it as a demonstration of how natural language understanding (NLU) can be used with pretrained, generic AI models, as well as a means to dispel intimidation around using machine learning.
Google AI researchers Ben Pietrzak, Steve Pucci, and Aaron Cohen in a blog post wrote that, Companies are using NLU to create digital personal assistants, customer service bots, and semantic search engines for reviews, forums and the news and the perception of using NLU and machine learning is costly and time-consuming prevents a lot of potential users from exploring its benefits.
Google Cloud AI Workshop, allows users to sort lines of text in a sheet using a range of AI models in these testing it requires filling out a form and awaiting emailed instructions about how to install it.
There are two Lists and will be sorted based on input text, including:
1. Semantic similarity: The lines more similar in meaning to the input will be ranked higher
2. Input-response: The lines that are the most appropriate conversational responses are ranked higher
Semantic Reactor can quickly add new question/answer pairs and test different phrasings, enabling developers to see how the model reacts to them and also can help write dialog for a chatbot.
It can also search through text using input-response, simply it can examine a list of potential responses and rank each according to which the model thinks is the most likely.
All Semantic Reactor models are published and available online, including, basic Online and Multilingual Online.
It compliments Google’s AutoML Natural Language, an extension of its Cloud AutoML machine learning platform to the natural language processing domain and supports for tasks like, sentiment analysis, entity extraction and classification, as well as a range of file.
