AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
This work reformulates dialog state tracking as a conversational semantic parsing task to overcome the limitations of slot filling

Conversational Semantic Parsing for Dialog State Tracking

EMNLP 2020, pp.8107-8117, (2020)

Cited by: 0|Views257
Full Text
Bibtex
Weibo

Abstract

We consider a new perspective on dialog state tracking (DST), the task of estimating a user’s goal through the course of a dialog. By formulating DST as a semantic parsing task over hierarchical representations, we can incorporate semantic compositionality, cross-domain knowledge sharing and co-reference. We present TreeDST, a dataset of ...More

Code:

Data:

0
Introduction
  • Task-based dialog systems, for example digital personal assistants, provide a linguistic user interface for all kinds of applications: from searching a database, booking a hotel, checking the weather to sending a text message.
  • Language understanding for other NLP applications is often formulated as semantic parsing, which is the task of converting a single-turn utterance to a graph-structured meaning representation.
  • Such meaning representations include logical forms, database queries and other programming languages
Highlights
  • Task-based dialog systems, for example digital personal assistants, provide a linguistic user interface for all kinds of applications: from searching a database, booking a hotel, checking the weather to sending a text message
  • Language understanding for other NLP applications is often formulated as semantic parsing, which is the task of converting a single-turn utterance to a graph-structured meaning representation
  • We introduce as baselines two state-ofthe-art slot-filling dialog state tracking” (DST) models based on encoderdecoders: they include COMER (Ren et al, 2019) which encodes the previous system response transcription and the previous user dialog state and decodes slot values; and TRADE (Wu et al, 2019) which encodes all utterances in the history
  • This work reformulates dialog state tracking as a conversational semantic parsing task to overcome the limitations of slot filling
  • Dialog states are represented as rooted relational graphs to encode compositionality, and encourage knowledge sharing across different domains, verbs, slot types and dialog participators
  • We proposed a conversational semantic parser that performs DST with an encoder-decoder model and a stack-based memory
Methods
  • Setup The authors split the TreeDST data into train (19,808), test (3,739) and development (3,733) sets.
  • The authors evaluate the proposed model with its “vanilla” decoder (TED-VANILLA) and its parent-pointer variant (TED-PP).
  • In both cases, the utterance encoder has 2 layers of 500 dimensions; the system act encoder and dialog state encoder have 2 layers of 200 dimensions; and the decoder has 2 LSTM layers of 500 dimensions.
  • The hyper-parameters were selected empirically based on an additional dataset that does not overlap with TreeDST
Conclusion
  • This work reformulates dialog state tracking as a conversational semantic parsing task to overcome the limitations of slot filling.
  • Dialog states are represented as rooted relational graphs to encode compositionality, and encourage knowledge sharing across different domains, verbs, slot types and dialog participators.
  • The authors proposed a conversational semantic parser that performs DST with an encoder-decoder model and a stack-based memory.
  • Experimental results show that the DST solution outperforms slot-filling-based trackers by a large margin
Tables
  • Table1: An example conversation in TreeDST with annotations. User and system utterances are marked in red and blue respectively. We use dot to represent tree edges and increased indentation levels to reveal multiple children attached to the same parent node. A sideies, making them vulnerable to language variations. Neural classification models (Mrksicet al., 2017; Mrksicand Vulic, 2018) alleviate the problem by learning distributed representations of user utterances. However, they still lack scalability to large by-side comparison between a dotted tree and its full unbounded output space (<a class="ref-link" id="cXu_2018_a" href="#rXu_2018_a">Xu and Hu, 2018</a>; Lee drawing can be found in Appendix A
  • Table2: Comparison of TreeDST with pertinent datasets for task-oriented dialogue
  • Table3: Results on the TreeDST test set tion. The advantage of the representation is that it
  • Table4: Results on the TreeDST development set, broken down by dialog phenomena slightly outperforms COMER and TRADE. The major difference is that our model encodes both past user and system representations; while the other
Download tables as Excel
Study subjects and analysis
slot-value pairs: 3
Tomorrow .time.equals.hour.equals.5 switching requires task reference resolution within the model; while multi-intent utterances tend to. Three slot-value pairs can be extracted: have more complex trees. Second, Figure 2 shows the vanilla model results (flight+object+source+location, London) (flight+object+departureDateTime+date +definedValue, Tomorrow) (flight+object+departureDateTime+time by turn index on the development set (black curve)

Reference
  • Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations.
    Google ScholarLocate open access versionFindings
  • Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider. 2013. Abstract meaning representation for sembanking. In Proceedings of the 7th linguistic annotation workshop and interoperability with discourse, pages 178–186.
    Google ScholarLocate open access versionFindings
  • Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 201Semantic parsing on Freebase from question-answer pairs. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1533–1544, Seattle, Washington, USA. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Inigo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Gasic. 2018. Multiwoz-a largescale multi-domain wizard-of-oz dataset for taskoriented dialogue modelling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 5016–5026.
    Google ScholarLocate open access versionFindings
  • Sonal Gupta, Rushin Shah, Mrinal Mohit, Anuj Kumar, and Mike Lewis. 2018. Semantic parsing for task oriented dialog using hierarchical representations. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Matthew Henderson, Blaise Thomson, and Jason D. Williams. 2014a. The second dialog state tracking challenge. In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pages 263–272, Philadelphia, PA, U.S.A. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Matthew Henderson, Blaise Thomson, and Steve Young. 2014b. Word-based dialog state tracking with recurrent neural networks. In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pages 292–299.
    Google ScholarLocate open access versionFindings
  • Robin Jia and Percy Liang. 2016. Data recombination for neural semantic parsing. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12–22.
    Google ScholarLocate open access versionFindings
  • Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. 3rd International Conference on Learning Representations.
    Google ScholarFindings
  • Thomas Kollar, Danielle Berry, Lauren Stuart, Karolina Owczarzak, Tagyoung Chung, Lambert Mathias, Michael Kayser, Branrd Snow, and Spyros Matsoukas. 2018. The alexa meaning representation language. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers), pages 177– 184.
    Google ScholarLocate open access versionFindings
  • Hwaran Lee, Jinsik Lee, and Tae-Yoon Kim. 2019. Sumbt: Slot-utterance matching for universal and scalable belief tracking. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5478–5483.
    Google ScholarLocate open access versionFindings
  • Sungjin Lee and Amanda Stent. 2016. Task lineages: Dialog state tracking for flexible interaction. In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 11–21.
    Google ScholarLocate open access versionFindings
  • Xiujun Li, Zachary C Lipton, Bhuwan Dhingra, Lihong Li, Jianfeng Gao, and Yun-Nung Chen. 2016. A user simulator for task-completion dialogues. arXiv preprint arXiv:1612.05688.
    Findings
  • Percy Liang, Michael I Jordan, and Dan Klein. 2013. Learning dependency-based compositional semantics. Computational Linguistics, 39(2):389–446.
    Google ScholarLocate open access versionFindings
  • Nikola Mrksic, Diarmuid O Seaghdha, Tsung-Hsien Wen, Blaise Thomson, and Steve Young. 2017. Neural belief tracker: Data-driven dialogue state tracking. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1777–1788.
    Google ScholarLocate open access versionFindings
  • Nikola Mrksicand Ivan Vulic. 2018. Fully statistical neural belief tracking. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 108–113.
    Google ScholarLocate open access versionFindings
  • Denis Peskov, Nancy Clarke, Jason Krone, Brigi Fodor, Yi Zhang, Adel Youssef, and Mona Diab. 2019. Multi-domain goal-oriented dialogues (multidogo): Strategies toward curating and annotating large scale dialogue data. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLPIJCNLP), pages 4518–4528.
    Google ScholarLocate open access versionFindings
  • Filip Radlinski, Krisztian Balog, Bill Byrne, and Karthik Krishnamoorthi. 2019. Coached conversational preference elicitation: A case study in understanding movie preferences. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 353–360.
    Google ScholarLocate open access versionFindings
  • Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta, and Pranav Khaitan. 20Towards scalable multi-domain conversational agents: The schema-guided dialogue dataset. arXiv preprint arXiv:1909.05855.
    Findings
  • Liliang Ren, Jianmo Ni, and Julian McAuley. 2019. Scalable and accurate dialogue state tracking via hierarchical sequence generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1876–1885.
    Google ScholarLocate open access versionFindings
  • Alexander Rudnicky and Wei Xu. 1999. An agendabased dialog management architecture for spoken language systems. In IEEE Automatic Speech Recognition and Understanding Workshop.
    Google ScholarLocate open access versionFindings
  • Jost Schatzmann, Blaise Thomson, Karl Weilhammer, Hui Ye, and Steve Young. 2007. Agenda-based user simulation for bootstrapping a pomdp dialogue system. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers, pages 149–152. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Pararth Shah, Dilek Hakkani-Tur, Gokhan Tur, Abhinav Rastogi, Ankur Bapna, Neha Nayak, and Larry Heck. 2018. Building a conversational agent overnight with dialogue self-play. arXiv preprint arXiv:1801.04871.
    Findings
  • Weiyan Shi, Kun Qian, Xuewei Wang, and Zhou Yu. 2019. How to build user simulators to train rl-based dialog systems. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLPIJCNLP), pages 1990–2000.
    Google ScholarLocate open access versionFindings
  • Oriol Vinyals, Lukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, and Geoffrey Hinton. 2015. Grammar as a foreign language. In Proceedings of NIPS 2015.
    Google ScholarLocate open access versionFindings
  • Tsung Hsien Wen, David Vandyke, Nikola Mrki, Milica Gasic, and Steve Young. 2017. A network-based end-to-end trainable task-oriented dialogue system. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers.
    Google ScholarLocate open access versionFindings
  • Jason Williams, Antoine Raux, and Matthew Henderson. 2016. The dialog state tracking challenge series: A review. Dialogue & Discourse, 7(3):4–33.
    Google ScholarLocate open access versionFindings
  • Chien-Sheng Wu, Andrea Madotto, Ehsan HosseiniAsl, Caiming Xiong, Richard Socher, and Pascale Fung. 2019. Transferable multi-domain state generator for task-oriented dialogue systems. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 808–819.
    Google ScholarLocate open access versionFindings
  • Puyang Xu and Qi Hu. 2018. An end-to-end approach for handling unknown slot values in dialogue state tracking. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1448–1457.
    Google ScholarLocate open access versionFindings
  • Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, et al. 2018. Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3911–3921.
    Google ScholarLocate open access versionFindings
Author
Devang Agrawal
Devang Agrawal
Shruti Bhargava
Shruti Bhargava
Joris Driesen
Joris Driesen
Federico Flego
Federico Flego
Dain Kaplan
Dain Kaplan
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科