Streamlined Decoder for Chinese Spoken Language Understanding
Pages 516 - 520
Abstract
As a critical component of Spoken Dialog System (SDS), spoken language understanding (SLU) attracts a lot of attention, especially for methods based on unaligned data. Recently, a new approach has been proposed that utilizes the hierarchical relationship between act-slot-value triples. However, it ignores the transfer of internal information which may record the intermediate information of the upper level and contribute to the prediction of the lower level. So, we propose a novel streamlined decoding structure with attention mechanism, which uses three successively connected RNN to decode act, slot and value respectively. On the first Chinese Audio-Textual Spoken Language Understanding Challenge (CATSLU), our model exceeds state-of-the-art model on an unaligned multi-turn task-oriented Chinese spoken dialogue dataset provided by the contest.
References
[1]
Lina M Rojas Barahona, Milica Gasic, Nikola Mrkšić, Pei-Hao Su, Stefan Ultes, Tsung-Hsien Wen, and Steve Young. 2016. Exploiting sentence and context representations in deep neural models for spoken language understanding. arXiv preprint arXiv:1610.04120(2016).
[2]
Alex Graves and Jürgen Schmidhuber. 2005. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks 18, 5-6 (2005), 602–610.
[3]
Matthew Henderson, Milica Gašić, Blaise Thomson, Pirros Tsiakoulis, Kai Yu, and Steve Young. 2012. Discriminative spoken language understanding using word confusion networks. In 2012 IEEE Spoken Language Technology Workshop (SLT). IEEE, 176–181.
[4]
Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780.
[5]
Chunxi Liu, Puyang Xu, and Ruhi Sarikaya. 2015. Deep contextual language understanding in spoken dialogue systems. In Sixteenth annual conference of the international speech communication association.
[6]
James H Martin and Daniel Jurafsky. 2009. Speech and language processing: An introduction to natural language processing, computational linguistics, and speech recognition. Pearson/Prentice Hall Upper Saddle River.
[7]
Christian Raymond and Giuseppe Riccardi. 2007. Generative and discriminative algorithms for spoken language understanding. In Eighth Annual Conference of the International Speech Communication Association.
[8]
Mike Schuster and Kuldip K Paliwal. 1997. Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing 45, 11 (1997), 2673–2681.
[9]
Tiejun Zhao Chengqing Zong Su Zhu, Zijian Zhao and Kai Yu. 2019. CATSLU: The 1st Chinese Audio-Textual Spoken Language Understanding Challenge. In 21st ACM International Conference on Multimodal Interaction.
[10]
Kaisheng Yao, Geoffrey Zweig, Mei-Yuh Hwang, Yangyang Shi, and Dong Yu. 2013. Recurrent neural networks for language understanding. In Interspeech. 2524–2528.
[11]
Lin Zhao and Zhe Feng. 2018. Improving Slot Filling in Spoken Language Understanding with Joint Pointer and Attention. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 426–431.
[12]
Zijian Zhao, Su Zhu, and Kai Yu. 2019. A Hierarchical Decoding Model for Spoken Language Understanding from Unaligned Data. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 7305–7309.
[13]
Su Zhu and Kai Yu. 2017. Encoder-decoder with focus-mechanism for sequence labelling based spoken language understanding. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 5675–5679.
Recommendations
CATSLU: The 1st Chinese Audio-Textual Spoken Language Understanding Challenge
ICMI '19: 2019 International Conference on Multimodal InteractionSpoken language understanding (SLU) is a key component of conversational dialogue systems, which converts user utterances into semantic representations. The previous works almost focus on parsing semantic from textual inputs (top hypothesis of speech ...
Joint dialog act segmentation and recognition in human conversations using attention to dialog context
Highlights- Proposed an encoder–decoder for joint dialog act segmentation and recognition.
- ...
AbstractA dialog act represents the communicative function of an utterance in a conversation, and thus provides informative cues for understanding, managing, and generating dialog. While most spoken dialog systems process user input and system ...
Salience modeling based on non-verbal modalities for spoken language understanding
ICMI '06: Proceedings of the 8th international conference on Multimodal interfacesPrevious studies have shown that, in multimodal conversational systems, fusing information from multiple modalities together can improve the overall input interpretation through mutual disambiguation. Inspired by these findings, this paper investigates ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2019
601 pages
ISBN:9781450368605
DOI:10.1145/3340555
Copyright © 2019 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 14 October 2019
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- Major Project of Zhijiang Lab
- NSFC
- SFSMBRP
- NSFB
- CETC
- BIGKE
Conference
ICMI '19
Acceptance Rates
Overall Acceptance Rate 453 of 1,080 submissions, 42%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 109Total Downloads
- Downloads (Last 12 months)5
- Downloads (Last 6 weeks)0
Reflects downloads up to 20 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format