Abstract Representation for Multi-Intent Spoken Language Understanding
Rim Abrougui, Géraldine Damnati, Johannes Heinecke, Frédéric Béchet
Abstract
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.
BibTeX
@inproceedings{icassp2023_abstractrepresen,
title = {Abstract Representation for Multi-Intent Spoken Language Understanding},
author = {Rim Abrougui and Géraldine Damnati and Johannes Heinecke and Frédéric Béchet},
booktitle = {ICASSP 2023},
year = {2023}
}