NLU Comparision: NeuralSpace, Google Dialogflow & IBM Watson
Whether you are using chatbots, voice bots, or process automation engines, they are all powered by Natural Language Understanding (NLU). Its main purpose is to understand the intent of the user, and extract relevant keywords (entities) from what they said or wrote to perform a relevant action.
In this blog, we compare the intent classification accuracies of three NLU service providers namely: NeuralSpace, Google’s Dialogflow & IBM Watson. This comparison has been done using Amazon Science’s MASSIVE dataset. Check out our blog on Evaluating NeuralSpace on the Amazon MASSIVE Dataset to know more about the dataset.
NeuralSpace’s language support for NLU extends to almost 100 languages, including low-resource languages spoken across Asia, the Middle East and Africa. Google’s Dialogflow offers language support of 96 different languages, while IBM Watson’s NLU supports 9 languages.
We cover only 9 languages in this comparison due to the limited language support IBM Watson’s NLU currently offers.
The table below shows the intent accuracies of Google’s Dialogflow ES, IBM Watson and NeuralSpace’s Language Understanding service, on the Amazon MASSIVE dataset. We compare the languages: Arabic, English, French, German, Italian, Japanese, Korean, Portuguese and Spanish.
A quick note on intent accuracy for the uninitiated:
The higher the accuracy, the better!
As can be seen above, NeuralSpace performs a staggering 4.96% better on average than Dialogflow and 3.04% better than IBM Watson on the above compared languages.
Check out our previous blog for a detailed comparison of NeuralSpace and Dialogflow’s intent classification service, where we compare accuracies over 28 languages. We also compare both platforms' feature set, language support, UI & UX.
Try out NeuralSpace’s Language Understanding service now.
Check out our Documentation to read more about the NeuralSpace Platform and its different services.
Join the NeuralSpace Slack Community to connect with us. Also, receive updates and discuss topics in NLP for low-resource languages with fellow developers and researchers.