A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU

arXiv:2405.02925v1 Announce Type: new
Abstract: Multi-intent natural language understanding (NLU) presents a formidable challenge due to the model confusion arising from multiple intents within a single utterance. While previous works train the model contrastively to increase the margin between different multi-intent labels, they are less suited to the nuances of multi-intent NLU. They ignore the rich information between the shared intents, which is beneficial to constructing a better embedding space, especially in low-data scenarios. We introduce a two-stage Prediction-Aware Contrastive …

abstract arxiv challenge cs.cl framework labels language language understanding multiple natural natural language nlu prediction stage train type understanding while