Hierarchical Context in Conversations for Spoken Language Understanding

The context in a language comes from their sequential patterns. For example, a sentence is formed by a sequence of words, a conversation is formed by a sequence of utterances, and so on. There have been many approaches to model such a deep concept. The neural approaches have been deployed to achieve state-of-the-art results.

Example: A piece of conversation with Dialogue Act annotation
Context-based Dialogue Act Recognition using Utterance-level DA Recognizer

Researcher in AI