End-to-end joint learning of natural language understanding and dialogue manager
Open accessThe DOI matches its Crossref record; 30 of the 33 references it cites were found in a registry or an index.
Abstract
Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance. Conventional approaches aggregate separate models of natural language understanding (NLU) and system action prediction (SAP) as a pipeline that is sensitive to noisy outputs of error-prone NLU. To address the issues, we propose an end-to-end deep recurrent neural network with limited contextual dialogue memory by jointly training NLU and SAP on DSTC4 multi-domain human-human dialogues. Experiments show that our proposed model significantly outperforms the state-of-the-art pipeline models for both NLU and SAP, which indicates that our joint model is capable of mitigating the affects of noisy NLU outputs, and NLU model can be refined by error flows backpropagating from the extra supervised signals of system actions.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“By incorporating natural language understanding (AI) techniques, we aim to minimize the user burden in self-monitoring, which requires minimal time and low health literacy levels [83,84].”
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
Lafferty, J., McCallum, A., & Pereira, F. C. N. (2001) · ScholarlyCommons (University of Pennsylvania) · Cited by 12,935
Bidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172
POMDP-Based Statistical Spoken Dialog Systems: A Review
Young, S., Gasic, M., Thomson, B., & Williams, J. D. (2013) · Proceedings of the IEEE · doi:10.1109/jproc.2012.2225812 · Cited by 882
A Network-based End-to-End Trainable Task-oriented Dialogue System
Wen, T.-H., Vandyke, D., Mrkšić, N., Gasic, M., Rojas Barahona, L. M., Su, P.-H., Ultes, S., & Young, S. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers · doi:10.18653/v1/e17-1042 · Cited by 778
Multi-Domain Joint Semantic Frame Parsing Using Bi-Directional RNN-LSTM
Hakkani-Tür, D., Tur, G., Celikyilmaz, A., Chen, Y.-N., Gao, J., Deng, L., & Wang, Y.-Y. (2016) · Interspeech 2016 · doi:10.21437/interspeech.2016-402 · Cited by 463
Self-citationUsing Recurrent Neural Networks for Slot Filling in Spoken Language Understanding
Mesnil, G., Dauphin, Y., Yao, K., Bengio, Y., Deng, L., Hakkani-Tur, D., He, X., Heck, L., Tur, G., Yu, D., et al. (2015) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2383614 · Cited by 461
Self-citationApplication of Deep Belief Networks for Natural Language Understanding
Sarikaya, R., Hinton, G. E., & Deoras, A. (2014) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2014.2303296 · Cited by 460
Word-Based Dialog State Tracking with Recurrent Neural Networks
Henderson, M., Thomson, B., & Young, S. (2014) · Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL) · doi:10.18653/v1/w14-4340 · Cited by 337
Research works printed but not linked: 1
- 10.3115/v1/w14-4340 · doi:10.3115/v1/w14-4340 · Paper page
Cited by
Cui, P., Wang, X., Pei, J., & Zhu, W. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2849727 · Cited by 1,274
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version
Serban, I. V., Lowe, R., Henderson, P., Charlin, L., & Pineau, J. (2018) · Dialogue & Discourse · doi:10.5087/dad.2018.101 · Cited by 150
Neural Approaches to Conversational AI
Gao, J., Galley, M., & Li, L. (2019) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000074 · Cited by 209
Self-citationDeep learning applications in single-cell genomics and transcriptomics data analysis
Erfanian, N., Heydari, A. A., Feriz, A. M., Iañez, P., Derakhshani, A., Ghasemigol, M., Farahpour, M., Razavi, S. M., Nasseri, S., Safarpour, H., et al. (2023) · Biomedicine & Pharmacotherapy · doi:10.1016/j.biopha.2023.115077 · Cited by 140
A Survey of Joint Intent Detection and Slot Filling Models in Natural Language Understanding
Weld, H., Huang, X., Long, S., Poon, J., & Han, S. C. (2023) · ACM Computing Surveys · doi:10.1145/3547138 · Cited by 167
Metadata
- Authors
- Yang, X., Chen, Y.-N., Hakkani-Tur, D., Crook, P., Li, X., Gao, J., & Deng, L.
- Affiliations
- University of Illinois Urbana-Champaign (US)
- National Taiwan University (TW)
- Microsoft (United States) (US)
- Venue
- 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2017-03
- Pages
- 5690-5694
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2560678344
- Cited by
- 80
- References
- 33
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 1 · 2023: 3 · 2022: 8 · 2021: 9 · 2020: 11 · 2019: 20 · 2018: 14 · 2017: 9
- FWCI
- 6.74
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Keywords
- natural language understanding, dialogue manager, dialogue policy learning, recurrent neural networks, dialogue systems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.