EMNLP Findings2022
Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models
Siddhant Arora, Siddharth Dalmia, Brian Yan, Florian Metze, Alan W. Black, Shinji Watanabe
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-toend 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 tokenlevel 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 scenarios. Our models outperform both cascaded and direct end-toend models on a labeling task of named entity recognition across SLU benchmarks. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on1
Related papers
- End-to-End Speech Recognition and Disfluency RemovalParia Jamshid Lou, Mark JohnsonEMNLP Findings 2020 · 20 citations
- ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text TranslationChenyang Le, Yao Qian, Long Zhou, Shujie Liu et al.NeurIPS 2023 · 21 citations
- Exploring Transfer Learning For End-to-End Spoken Language UnderstandingSubendhu Rongali, Beiye Liu, Liwei Cai, Konstantine Arkoudas et al.AAAI 2021 · 26 citations
- PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language UnderstandingTrang Le, Daniel Lazar, Suyoun Kim, Shan Jiang et al.EMNLP Findings 2024
- Semantic Role Labeling from Chinese Speech via End-to-End LearningHuiyao Chen, Xinxin Li, Meishan Zhang, Min ZhangACL Findings 2024 · 5 citations
