Abstract: Technologies relating to improving performance of a computer-implemented model that acts as a multi-class classifier are described herein. A chatbot includes the computer-implemented model, and the computer-implemented model receives natural language input from end users. A subset of the natural language inputs are identified as training examples that are to be used to update the computer-implemented model, wherein the natural language inputs are identified as the training examples based upon comparisons between scores for the natural language inputs output by different classifiers of the computer-implemented model. The training examples are labeled by a developer, and the computer-implemented model is updated based upon the labeled training examples.

Abstract: Described herein is a mechanism for improving the accuracy of a language model interpreting short input utterances. A language model operates in a stateless manner, only ascertaining the intents and/or entities associated with a presented input utterance. To increase the accuracy, two language understanding models are trained. One is trained using only input utterances. The second is trained using input utterance-prior dialog context pairs. The prior dialog context is previous intents and/or entities already determined from the utterances in prior turns of the dialog. When input is received, the language understanding model decides whether the input comprises only an utterance or an utterance and prior dialog context. The appropriate trained machine learning model is selected and the intents and/or entities associated with the input determined by the selected machine learning model.

Abstract: Described herein is a mechanism for improving the accuracy of a language model interpreting short input utterances. A language model operates in a stateless manner, only ascertaining the intents and/or entities associated with a presented input utterance. To increase the accuracy, two language understanding models are trained. One is trained using only input utterances. The second is trained using input utterance-prior dialog context pairs. The prior dialog context is previous intents and/or entities already determined from the utterances in prior turns of the dialog. When input is received, the language understanding model decides whether the input comprises only an utterance or an utterance and prior dialog context. The appropriate trained machine learning model is selected and the intents and/or entities associated with the input determined by the selected machine learning model.

Abstract: Technologies relating to improving performance of a computer-implemented model that acts as a multi-class classifier are described herein. A chatbot includes the computer-implemented model, and the computer-implemented model receives natural language input from end users. A subset of the natural language inputs are identified as training examples that are to be used to update the computer-implemented model, wherein the natural language inputs are identified as the training examples based upon comparisons between scores for the natural language inputs output by different classifiers of the computer-implemented model. The training examples are labeled by a developer, and the computer-implemented model is updated based upon the labeled training examples.