End-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Spoken language understanding (SLU) is a core component of a spoken dialogue system. In the traditional architecture of dialogue systems, the SLU component treats each utterance independent of each other, and then the following components aggregate the multi-turn information in the separate phases. However, there are two challenges: 1) errors from previous turns may be propagated and then degrade the performance of the current turn; 2) knowledge mentioned in the long history may not be carried into the current turn. This paper addresses the above issues by proposing an architecture using end-to-end memory networks to model knowledge carryover in multi-turn conversations, where utterances encoded with intents and slots can be stored as embeddings in the memory and the decoding phase applies an attention model to leverage previously stored semantics for intent prediction and slot tagging simultaneously. The experiments on Microsoft Cortana conversational data show that the proposed memory network architecture can effectively extract salient semantics for modeling knowledge carryover in the multi-turn conversations and outperform the results using the state-of-the-art recurrent neural network framework (RNN) designed for single-turn SLU.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Elman, J. L. (1990) · Cognitive Science · doi:10.1207/s15516709cog1402_1 · Cited by 11,212
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“RNNs employing either of these recurrent units have been shown to perform well in tasks that require capturing long-term dependencies [15, 30, 31, 32].”
BackgroundSukhbaatar, S., Szlam, A., Weston, J., & Fergus, R. (2015) · arXiv · doi:10.48550/arxiv.1503.08895 · Cited by 1,345
Graves, A., Wayne, G., & Danihelka, I. (2014) · arXiv · doi:10.48550/arxiv.1410.5401 · Cited by 1,058 · cited 1×
“Recently there has been a resurgence in computational models using explicit storage and a notion of attention [22, 23, 24, 25]; manipulating such a storage allows multiple computational steps and can model long-term dependencies in sequential utterances.”
BackgroundEasy contextual intent prediction and slot detection
Bhargava, A., Celikyilmaz, A., Hakkani-Tur, D., & Sarikaya, R. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639291 · Cited by 91 · cited 2×
“incorporated the information from previous intra-session utterances into the SLU tasks on a given utterance by applying SVM-HMMs to sequence tagging and obtained the improvement [17].”
Method
Cited by
Deep Reinforcement Learning: An Overview
Li, Y. (2017) · arXiv · doi:10.48550/arxiv.1701.07274 · Cited by 762
“, 2016b). Li et al. (2016c) proposed to use deep RL to generate dialogue s to model future reward for better informativity, coherence, and ease of answering, to attemp to address the issues in the sequence to sequence models based on Sutskever et al. (2014): the myop ia and misalignment of maximizing the probability o…”
BackgroundMethodInfluentialMulti-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-citationTowards End-to-End Reinforcement Learning of Dialogue Agents for Information Access
Dhingra, B., Li, L., Li, X., Gao, J., Chen, Y.-N., Ahmed, F., & Deng, L. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1045 · Cited by 272
Self-citationRecent advances in deep learning based dialogue systems: a systematic survey
Ni, J., Young, T., Pandelea, V., Xue, F., & Cambria, E. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10248-8 · Cited by 264
Joint Slot Filling and Intent Detection via Capsule Neural Networks
Zhang, C., Li, Y., Du, N., Fan, W., & Yu, P. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1519 · Cited by 253
End-to-end joint learning of natural language understanding and dialogue manager
Yang, X., Chen, Y.-N., Hakkani-Tur, D., Crook, P., Li, X., Gao, J., & Deng, L. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7953246 · Cited by 80
Self-citationMulti-turn Intent Determination for Goal-oriented Dialogue systems
Abro, W. A., Qi, G., Gao, H., Khan, M. A., & Ali, Z. (2019) · 2019 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852246 · Cited by 23
Metadata
- Authors
- Chen, Y.-N., Hakkani-Tür, D., Tur, G., Gao, J., & Deng, L.
- Venue
- Interspeech 2016
- Publisher
- ISCA
- Published
- 2016-09-08
- Pages
- 3245-3249
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2473965551
- Cited by
- 144
- References
- 7
- FWCI
- 15.97
- Type
- conference paper
- Language
- en
- Open access
- closed
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.