Intent Classification is the task of correctly labeling a natural language utterance from a predetermined set of intents
User queries for a real-world dialog system may sometimes fall outside the scope of the system's capabilities, but appropriate system responses will enable smooth processing throughout the human-computer interaction.
Neural Language Models (NLM), when trained and evaluated with context spanning multiple utterances, have been shown to consistently outperform both conventional n-gram language models and NLMs that use limited context.
We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks.
We propose a simple and robust integration method for the E2E SLU network with novel Interface, Continuous Token Interface (CTI), the junctional representation of the ASR and NLU networks when both networks are pre-trained with the same vocabulary.
Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain.
We build a word-free natural language understanding module that does intent recognition and slot identification from these phonetic transcription.
This paper presents a production Semi-Supervised Learning (SSL) pipeline based on the student-teacher framework, which leverages millions of unlabeled examples to improve Natural Language Understanding (NLU) tasks.
The understanding of the human language is quantified by identifying intents and entities.