Abstract
Lattices are compact representations that can encode multiple speech recognition hypotheses in spoken language understanding tasks. Previous work has extended the pre-trained transformer to model lattice inputs and achieved significant improvements in natural language processing tasks. However, these models do not consider the global probability distribution of lattices path and the correlation among multiple speech recognition hypotheses. In this paper, we propose an associated Lattice-BERT, an extension of BERT that is tailored for spoken language understanding (SLU). Associated Lattice-BERT augments self-attention with positional relation representations and lattice scores to incorporate lattice structure. We further design a lattice confusion-aware attention mechanism in the prediction layer to push the model to learn from the association information between the lattice confusion paths, which mitigates the impact of the Automatic Speech Recognizer (ASR) errors on the model. We apply the proposed model to a spoken language understanding task, the experiments on the datasets of intention detection recognition show that our proposed method outperforms the strong baselines when evaluated on spoken inputs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goo, C., et al.: Slot-gated modeling for joint slot filling and intent prediction. In: NAACL-HLT (2), pp. 753–757 (2018)
Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of EMNLP, pp. 1631–1642. ACL (2013)
Tai, K., et al.: Improved semantic representations from tree-structured long short-term memory networks. In: Proceedings of ACL, pp. 1556–1566. ACL (2015)
Zhu, X., Sobhani, P., Guo, H.: Long short-term memory over recursive structures. In: Proceedings of ICML, pp. 1604–1612. ICML (2015)
Ladhak, F., et al.: LatticeRnn: recurrent neural networks over lattices. In: Interspeech 2016 (2016)
Sperber, M., et al.: Self-attentional models for lattice inputs. In: Proceedings of ACL, pp. 1185–1197. ACL (2019)
Devlin, J., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL, pp. 4171–4186. ACL (2019)
Lai, Y., et al.: Lattice-BERT: leveraging multi-granularity representations in Chinese pre-trained language models. In: Proceedings of NAACL, pp. 1716–1731. ACL (2021)
Rabiner, L.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)
Zhang, P., et al.: Lattice transformer for speech translation. In: Proceedings of ACL, pp. 6475–6484. ACL (2019)
Saade, A., et al.: Spoken language understanding on the edge. In: 2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing - NeurIPS Edition (EMC2-NIPS), pp. 57–61 (2019)
Coucke, A., et al.: Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. CoRR abs/1805.10190 (2018)
Bastianelli, E., et al.: SLURP: a spoken language understanding resource package. In: Proceedings of EMNLP, pp. 7252–7262. ACL (2020)
Huang, C., Chen, Y.: Learning spoken language representations with neural lattice language modeling. In: Proceedings of ACL, pp. 3764–3769. ACL (2020)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zou, Y., Sun, H., Chen, Z. (2021). Associated Lattice-BERT for Spoken Language Understanding. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1517. Springer, Cham. https://doi.org/10.1007/978-3-030-92310-5_67
Download citation
DOI: https://doi.org/10.1007/978-3-030-92310-5_67
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92309-9
Online ISBN: 978-3-030-92310-5
eBook Packages: Computer ScienceComputer Science (R0)