Abstract Representation for Multi-Intent Spoken Language Understanding

Current sequence tagging models based on Deep Neural Network models with pretrained language models achieve almost perfect results on many SLU benchmarks with a flat semantic annotation at the token level such as ATIS or SNIPS. When dealing with more complex human-machine interactions (multi-domain,...

Full description

Saved in:
Bibliographic Details
Main Authors: Abrougui, Rim, Damnati, Geraldine, Heinecke, Johannes, Bechet, Frederic
Format: Conference Proceeding
Language:English
Subjects:
Annotations
Deep learning
Human computer interaction
Natural Language Understanding
Natural languages
Neural networks
Semantics
sequence tagging
sequence-to-sequence models
Spoken Language Understanding
Tagging
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Current sequence tagging models based on Deep Neural Network models with pretrained language models achieve almost perfect results on many SLU benchmarks with a flat semantic annotation at the token level such as ATIS or SNIPS. When dealing with more complex human-machine interactions (multi-domain, multi-intent, dialog context), relational semantic structures are needed in order to encode the links between slots and intents within an utterance and through dialog history. We propose in this study a new way to project annotation in an abstract structure with more compositional expressive power and a model to directly generate this abstract structure. We evaluate it on the MultiWoz dataset in a contextual SLU experimental setup. We show that this projection can be used to extend the existing flat annotations towards graph-based structures.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10095062