Dialog State Tracking: A Neural Reading Comprehension Approach
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Dialog state tracking is used to estimate the current belief state of a dialog given all the preceding conversation.Machine reading comprehension, on the other hand, focuses on building systems that read passages of text and answer questions that require some understanding of passages.We formulate dialog state tracking as a reading comprehension task to answer the question what is the state of the current dialog?after reading conversational context.In contrast to traditional state tracking methods where the dialog state is often predicted as a distribution over a closed set of all the possible slot values within an ontology, our method uses a simple attention-based neural network to point to the slot values within the conversation.Experiments on MultiWOZ-2.0 cross-domain dialog dataset show that our simple system can obtain similar accuracies compared to the previous more complex methods.By exploiting recent advances in contextual word embeddings, adding a model that explicitly tracks whether a slot value should be carried over to the next turn, and combining our method with a traditional joint state tracking method that relies on closed set vocabulary, we can obtain a joint-goal accuracy of 47.33% on the standard test split, exceeding current state-of-the-art by 11.75%**.
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 7×
“The contextual embedding BERT (Devlin et al., 2018) can give us around 2% gains.”
BackgroundMethodInfluentialSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 2×
“, 2017) or to free-form text by employing seq-to-seq models (Sutskever et al., 2014).”
BackgroundDeep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983 · cited 2×
“The recent advancements in the neural representation of words includes using character embeddings (Seo et al., 2016) and more recently using contextualized embeddings such as ELMO (Peters et al., 2018) and BERT (Devlin et al., 2018).”
BackgroundMethodSQuAD: 100,000+ Questions for Machine Comprehension of Text
Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1264 · Cited by 6,208 · cited 3×
“On the other hand, reading comprehension tasks (Rajpurkar et al., 2016; Chen et al., 2017; Reddy et al., 2019) require us to find the answer spans within the given passage and hence state-of-the-art models are developed in such a way that a fixed vocabulary for an answer is usually not required.”
BackgroundMethodTeaching Machines to Read and Comprehend
Hermann, K. M., Kočiský, T., Grefenstette, E., Espeholt, L., Kay, W., Suleyman, M., & Blunsom, P. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.03340 · Cited by 2,521 · cited 2×
“In these tasks, an answer type can be cloze-style as in CNN/Daily Mail (Hermann et al., 2015), multiple choice as in MCTest (Richardson et al., 2013), span prediction as in SQuaD (Rajpurkar et al., 2016), and free-form answer as in Narra-tiveQA (Koˇcisk`y et al., 2018).”
MethodReading Wikipedia to answer open-domain questions
Chen, D., Fisch, A., Weston, J., & Bordes, A. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1171 · Cited by 1,546 · cited 4×
“We use a simple attention-based neural network model to find answer spans by directly pointing to the to-kens within the dialog, which is similar to Chen et al. (2017).”
BackgroundMethodInfluentialBidirectional Attention Flow for Machine Comprehension
Seo, M. J., Kembhavi, A., Farhadi, A., & Hajishirzi, H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01603 · Cited by 1,445 · cited 2×
“Deep Contextual Word Embeddings The recent advancements in the neural representation of words includes using character embeddings (Seo et al., 2016) and more recently using contextualized embeddings such as ELMO (Peters et al.”
BackgroundMethodRACE: Large-scale ReAding Comprehension Dataset From Examinations
Lai, G., Xie, Q., Liu, H., Yang, Y., & Hovy, E. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1082 · Cited by 1,044 · cited 2×
“generic and can be extended to multiple choice questions by employing bilinear product for different types (Lai et al., 2017) or to free-form text by employing seq-to-seq models (Sutskever et al.”
BackgroundMultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
Budzianowski, P., Wen, T.-H., Tseng, B.-H., Casanueva, I., Ultes, S., Ramadan, O., & Gašić, M. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1547 · Cited by 1,028
CoQA: A Conversational Question Answering Challenge
Reddy, S., Chen, D., & Manning, C. D. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00266 · Cited by 975 · cited 1×
“On the other hand, reading comprehension tasks (Rajpurkar et al., 2016; Chen et al., 2017; Reddy et al., 2019) require us to find the answer spans within the given passage and hence state-of-the-art models are developed in such a way that a fixed vocabulary for an answer is usually not required.”
BackgroundPartially observable Markov decision processes for spoken dialog systems
Williams, J. D., & Young, S. (2007) · Computer Speech & Language · doi:10.1016/j.csl.2006.06.008 · Cited by 853 · cited 1×
“In generative approaches, a dialog is modeled as a dynamic Bayesian network where true dialog state and true user action are unobserved random variables (Williams and Young, 2007); whereas the discriminative approaches are directly modeling the distribution over the dialog state given arbitrary input features.”
BackgroundLinguistic Knowledge and Transferability of Contextual Representations
Liu, N. F., Gardner, M., Belinkov, Y., Peters, M. E., & Smith, N. A. (2019) · Proceedings of the 2019 Conference of the North · doi:10.18653/v1/n19-1112 · Cited by 621 · cited 1×
“Given their wide applicability (Liu et al., 2019), we employ these architectures in our dialog state tracking task.”
MethodMCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text
Richardson, M., Burges, C. J. C., & Renshaw, E. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1020 · Cited by 610 · cited 1×
“In these tasks, an answer type can be cloze-style as in CNN/Daily Mail (Hermann et al., 2015), multiple choice as in MCTest (Richardson et al., 2013), span prediction as in SQuaD (Rajpurkar et al., 2016), and free-form answer as in Narra-tiveQA (Koˇcisk`y et al., 2018).”
MethodThe NarrativeQA Reading Comprehension Challenge
Kočiský, T., Schwarz, J., Blunsom, P., Dyer, C., Hermann, K. M., Melis, G., & Grefenstette, E. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00023 · Cited by 596 · cited 1×
“In these tasks, an answer type can be cloze-style as in CNN/Daily Mail (Hermann et al., 2015), multiple choice as in MCTest (Richardson et al., 2013), span prediction as in SQuaD (Rajpurkar et al., 2016), and free-form answer as in Narra-tiveQA (Koˇcisk`y et al., 2018).”
MethodTransferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
Wu, C.-S., Madotto, A., Hosseini-Asl, E., Xiong, C., Socher, R., & Fung, P. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1078 · Cited by 415 · cited 1×
“**We note that after publication, a new state-of-the-art can now be obtained with a similar attention mechanism followed by a enoder-decoder architecture (Wu et al., 2019).”
BackgroundLarge-Scale Multi-Domain Belief Tracking with Knowledge Sharing
Ramadan, O., Budzianowski, P., & Gašić, M. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-2069 · Cited by 158 · cited 2×
“0 corpus (Budzianowski et al., 2018; Ramadan et al., 2018).”
Factored partially observable Markov decision processes for dialogue management
Williams, J. D., Poupart, P., & Young, S. J. (2005) · Cambridge University Engineering Department Publications Database · Cited by 120
Scalable multi-domain dialogue state tracking
Rastogi, A., Hakkani-Tur, D., & Heck, L. (2017) · 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) · doi:10.1109/asru.2017.8268986 · Cited by 110 · cited 1×
“To address these concerns, a class of methods employing scoring mechanisms to predict the slot value from a endogenously defined set of candidates have been proposed (Rastogi et al., 2017; Goel et al., 2018).”
Self-citationSDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
Zhu, C., Zeng, M., & Huang, X. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.03593 · Cited by 100 · cited 1×
“…models into our dialog state tracking pipeline, a slot carryover model to help the tracker make a binary decision whether the slot values from the previous turn should be used; a slot type model to predict whether the answer is { Yes , No , DontCare , Span } , which is similar to Zhu et al. (2018).”
MethodInfluentialAn End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog
Liu, B., & Lane, I. R. (2017) · Interspeech (USB) · doi:10.21437/interspeech.2017-1326 · Cited by 93 · cited 3×
“As shown in oracle ablation studies in Liu and Lane (2017).”
BackgroundMethodHyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking
Goel, R., Paul, S., & Hakkani-Tür, D. Z. (2019) · Interspeech (USB) · doi:10.21437/interspeech.2019-1863 · Cited by 93
Dialog state tracking, a machine reading approach using Memory Network
Pérez, J., & Liu, F. (2017) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/e17-1029 · Cited by 68 · cited 1×
“Previously, Perez and Liu (2017) also formulated state tracking as a machine reading comprehension problem.”
BackgroundGlobal-Locally Self-Attentive Dialogue State TrackerPreprint
Zhong, V., Xiong, C., & Socher, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.09655 · Cited by 67
An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking
Xu, P., & Hu, Q. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1134 · Cited by 38 · cited 1×
“Perhaps, the most similar technique to our work is the pointer networks proposed by Xu and Hu (2018) wherein an attention-based mechanism is employed to point the start and end token of a slot value.”
MethodFlexible and Scalable State Tracking Framework for Goal-Oriented Dialogue SystemsPreprint
Goel, R., Paul, S., Chung, T., Lecomte, J., Mandal, A., & Hakkani-Tür, D. Z. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.12891 · Cited by 21 · cited 2×
“To address these concerns, a class of methods employing scoring mechanisms to predict the slot value from a endogenously defined set of candidates have been proposed (Rastogi et al., 2017; Goel et al., 2018).”
BackgroundSelf-citation
Cited by
Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey
Min, B., Ross, H., Sulem, E., Veyseh, A. P. B., Nguyen, T. H., Sainz, O., Agirre, E., Heintz, I., & Roth, D. (2024) · ACM Computing Surveys · doi:10.1145/3605943 · Cited by 1,387
“[50] formulated the dialogue state tracking as a QA problem.”
BackgroundEvent Extraction as Machine Reading Comprehension
Liu, J., Chen, Y., Liu, K., Bi, W., & Liu, X. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.128 · Cited by 303
Explaining machine learning models with interactive natural language conversations using TalkToModel
Slack, D., Krishna, S., Lakkaraju, H., & Singh, S. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00692-8 · Cited by 125
Metadata
- Authors
- Gao, S., Sethi, A., Agarwal, S., Chung, T., & Hakkani-Tur, D.
- Venue
- Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
- Published
- 2019
- Pages
- 264-273
- OpenAlex
- W2979400990
- Cited by
- 164
- References
- 28
- FWCI
- 12.62
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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.