Token-level Sequence Labeling For Spoken Language Understanding Using Compositional End-to-end Models

Abstract

End-to-end spoken language understanding (SLU) systems are gaining popularity over cascaded approaches due to their simplicity and ability to avoid error propagation. However, these systems model sequence labeling as a sequence prediction task causing a divergence from its well-established token-level tagging formulation. We build compositional end-to-end SLU systems that explicitly separate the added complexity of recognizing spoken mentions in SLU from the NLU task of sequence labeling. By relying on intermediate decoders trained for ASR, our end-to-end systems transform the input modality from speech to token-level representations that can be used in the traditional sequence labeling framework. This composition of ASR and NLU formulations in our end-to-end SLU system offers direct compatibility with pre-trained ASR and NLU systems, allows performance monitoring of individual components and enables the use of globally normalized losses like CRF, making them attractive in practical sc

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyarora2022token

Related papers

• Speech-language Pre-training For End-to-end Spoken Language Understanding (2021)9.41
• End-to-end Architectures For Asr-free Spoken Language Understanding (2019)8.60
• Integrating Pretrained ASR And LM To Perform Sequence Generation For Spoken Language Understanding (2023)5.24
• Recent Advances In End-to-end Spoken Language Understanding (2019)8.09
• Do As I Mean, Not As I Say: Sequence Loss Training For Spoken Language Understanding (2021)6.77
• Speech To Semantics: Improve ASR And NLU Jointly Via All-neural Interfaces (2020)9.03
• Large-scale Transfer Learning For Low-resource Spoken Language Understanding (2020)2.26
• Improving End-to-end Models For Set Prediction In Spoken Language Understanding (2022)0.00