research-article

Free access

Interactive semantic parsing for if-then recipes via hierarchical reinforcement learning

AUTHORs:

Huan SunAuthors Info & Claims

AAAI'19/IAAI'19/EAAI'19: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence

Article No.: 314, Pages 2547 - 2554

https://doi.org/10.1609/aaai.v33i01.33012547

Published: 27 January 2019 Publication History

PDF eReader Publisher Site

Abstract

Given a text description, most existing semantic parsers synthesize a program in one shot. However, it is quite challenging to produce a correct program solely based on the description, which in reality is often ambiguous or incomplete. In this paper, we investigate interactive semantic parsing, where the agent can ask the user clarification questions to resolve ambiguities via a multi-turn dialogue, on an important type of programs called "If-Then recipes." We develop a hierarchical reinforcement learning (HRL) based agent that significantly improves the parsing performance with minimal questions to the user. Results under both simulation and human evaluation show that our agent substantially outperforms non-interactive semantic parsers and rule-based agents.

References

[1]

Azaria, A.; Krishnamurthy, J.; and Mitchell, T. M. 2016. Instructable intelligent personal agent. In AAAI, 2681-2689.

[2]

Beltagy, I., and Quirk, C. 2016. Improved semantic parsers for if-then statements. In ACL, volume 1, 726-736.

[3]

Berant, J.; Chou, A.; Frostig, R.; and Liang, P. 2013. Semantic parsing on freebase from question-answer pairs. In EMNLP, 1533-1544.

[4]

Campagna, G.; Ramesh, R.; Xu, S.; Fischer, M.; and Lam, M. S. 2017. Almond: The architecture of an open, crowdsourced, privacy-preserving, programmable virtual assistant. In WWW, 341-350.

[5]

Center, O. S. 1987. Ohio supercomputer center, http://osc.edu/ark:/19495/f5slph73.

[6]

Chaurasia, S., and Mooney, R. I. 2017. Dialog for language to code. In IJCNLP, volume 2, 175-180.

[7]

Dhingra, B.; Li, L.; Li, X.; Gao, I.; Chen, Y.-N.; Ahmed, F.; and Deng, L. 2017. Towards end-to-end reinforcement learning of dialogue agents for information access. In ACL.

[8]

Dietterich, T. G. 2000. Hierarchical reinforcement learning with the maxq value function decomposition. Journal of Artificial Intelligence Research 13:227-303.

[9]

Dong, L., and Lapata, M. 2016. Language to logical form with neural attention. In ACL, volume 1, 33-43.

[10]

Dong, L.; Quirk, C.; and Lapata, M. 2018. Confidence modeling for neural semantic parsing. In ACL.

[11]

Gao, I.; Galley, M.; and Li, L. 2018. Neural approaches to conversational ai. arXiv preprint arXiv: 1809.08267.

[12]

Gordon, D.; Kembhavi, A.; Rastegari, M.; Redmon, I.; Fox, D.; and Farhadi, A. 2017. Iqa: Visual question answering in interactive environments. arXiv preprint arXiv: 1712.03316.

[13]

Guo, X.; Klinger, T.; Rosenbaum, C.; Bigus, I. P.; Campbell, M.; Kawas, B.; Talamadupula, K.; Tesauro, G.; and Singh, S. 2016. Learning to query, reason, and answer questions on ambiguous texts.

[14]

Gur, I.; Yavuz, S.; Su, Y.; and Yan, X. 2018. Dialsql: Dialogue based structured query generation. In ACL, 1339-1349.

[15]

He, L.; Michael, I.; Lewis, M.; and Zettlemoyer, L. 2016. Human-in-the-loop parsing. In EMNLP, 2337-2342.

[16]

Iyer, S.; Konstas, I.; Cheung, A.; Krishnamurthy, I.; and Zettlemoyer, L. 2017. Learning a neural semantic parser from user feedback. In ACL, volume 1, 963-973.

[17]

Kulkarni, T. D.; Narasimhan, K.; Saeedi, A.; and Tenenbaum, I. 2016. Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation. In NIPS.

[18]

Li, F., and Jagadish, H. 2014. Constructing an interactive natural language interface for relational databases. VLDB.

[19]

Li, I.; Miller, A. H.; Chopra, S.; Ranzato, M.; and Weston, I. 2016a. Dialogue learning with human-in-the-loop. arXiv preprint arXiv: 1611.09823.

[20]

Li, X.; Lipton, Z. C.; Dhingra, B.; Li, L.; Gao, I.; and Chen, Y.-N. 2016b. A user simulator for task-completion dialogues. arXiv preprint arXiv: 1612.05688.

[21]

Li, H.; Min, M. R.; Ge, Y.; and Kadav, A. 2017. A context-aware attention network for interactive question answering. In SIGKDD, 927-935. ACM.

[22]

Liu, C.; Chen, X.; Shin, E. C.; Chen, M.; and Song, D. 2016. Latent attention for if-then program synthesis. In NIPS.

[23]

Mnih, V.; Kavukcuoglu, K.; Silver, D.; Rusu, A. A.; Veness, J.; Bellemare, M. G.; Graves, A.; Riedmiller, M.; Fidjeland, A. K.; Ostrovski, G.; et al. 2015. Human-level control through deep reinforcement learning. Nature 518(7540):529.

[24]

Parr, R., and Russell, S. I. 1998. Reinforcement learning with hierarchies of machines. In NIPS, 1043-1049.

[25]

Pavlick, E.; Rastogi, P.; Ganitkevitch, I.; Van Durme, B.; and Callison-Burch, C. 2015. Ppdb 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification. In ACL-IJCNLP, 425-430.

[26]

Peng, B.; Li, X.; Li, L.; Gao, J.; Celikyilmaz, A.; Lee, S.; and Wong, K.-F. 2017. Composite task-completion dialogue policy learning via hierarchical deep reinforcement learning. In EMNLP, 2221-2230.

[27]

Peng, B.; Li, X.; Gao, J.; Liu, J.; and Wong, K.-F. 2018. Deep dyna-q: Integrating planning for task-completion dialogue policy learning. In ACL, volume 1, 2182-2192.

[28]

Quirk, C.; Mooney, R. I.; and Galley, M. 2015. Language to code: Learning semantic parsers for if-this-then-that recipes. In ACL, 878-888.

[29]

Rabinovich, M.; Stern, M.; and Klein, D. 2017. Abstract syntax networks for code generation and semantic parsing. In ACL, volume 1, 1139-1149.

[30]

Su, Y.; Awadallah, A. H.; Khabsa, M.; Pantel, P.; Gamon, M.; and Encarnacion, M. 2017. Building natural language interfaces to web apis. In CIKM, 177-186. ACM.

[31]

Su, Y.; Awadallah, A. H.; Wang, M.; and White, R. W. 2018. Natural language interfaces with fine-grained user interaction: A case study on web apis. In SIGIR.

[32]

Sutton, R. S.; Precup, D.; and Singh, S. 1999. Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artificial intelligence 112(1-2): 181-211.

[33]

Tessler, C.; Givony, S.; Zahavy, T.; Mankowitz, D. I.; and Mannor, S. 2017. A deep hierarchical approach to lifelong learning in minecraft. In AAAI, volume 3, 6.

Digital Library

[34]

Thomason, J.; Zhang, S.; Mooney, R. J.; and Stone, P. 2015. Learning to interpret natural language commands through human-robot dialog. In IJCAI, 1923-1929.

[35]

Ur, B.; Pak Yong Ho, M.; Brawner, S.; Lee, J.; Mennicken, S.; Picard, N.; Schulze, D.; and Littman, M. L. 2016. Trigger-action programming in the wild: An analysis of 200,000 ifttt recipes. In CHI, 3227-3231. ACM.

[36]

Wang, X.; Chen, W.; Wu, J.; Wang, Y.-F.; and Wang, W. Y. 2017. Video captioning via hierarchical reinforcement learning. arXiv preprint arXiv: 1711.11135.

[37]

Williams, R. I. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. In Reinforcement Learning. Springer. 5-32.

[38]

Yih, S. W.-t; Chang, M.-W.; He, X.; and Gao, J. 2015. Semantic parsing via staged query graph generation: Question answering with knowledge base.

[39]

Yin, P., and Neubig, G. 2017. A syntactic neural model for general-purpose code generation. arXiv: 1704.01696.

[40]

Zhang, J.; Zhao, T.; and Yu, Z. 2018. Multimodal hierarchical reinforcement learning policy for task-oriented visual dialog. arXiv preprint arXiv: 1805.03257.

[41]

Zhong, V.; Xiong, C.; and Socher, R. 2017. Seq2sql: Generating structured queries from natural language using reinforcement learning. CoRR abs/1709.00103.

[42]

Zhou, P.; Shi, W.; Tian, J.; Qi, Z.; Li, B.; Hao, H.; and Xu, B. 2016. Attention-based bidirectional long short-term memory networks for relation classification. In ACL, 207-212.

Cited By

Peretz GArraf MRadinsky KChen HDuh WHuang HKato MMothe JPoblete B(2023)What If: Generating Code to Answer Simulation Questions in Chemistry TextsProceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3539618.3591783(1335-1344)Online publication date: 19-Jul-2023
https://dl.acm.org/doi/10.1145/3539618.3591783
Yusuf IJiang LLo DRastogi ATufano RBavota GArnaoudova VHaiduc S(2022)Accurate generation of trigger-action programs with domain-adapted sequence-to-sequence learningProceedings of the 30th IEEE/ACM International Conference on Program Comprehension10.1145/3524610.3527922(99-110)Online publication date: 16-May-2022
https://dl.acm.org/doi/10.1145/3524610.3527922
Xu FVasilescu BNeubig G(2022)In-IDE Code Generation from Natural Language: Promise and ChallengesACM Transactions on Software Engineering and Methodology10.1145/348756931:2(1-47)Online publication date: 4-Mar-2022
https://dl.acm.org/doi/10.1145/3487569

Index Terms

Interactive semantic parsing for if-then recipes via hierarchical reinforcement learning
1. Computing methodologies
  1. Artificial intelligence
  2. Machine learning
    1. Learning paradigms

Index terms have been assigned to the content through auto-classification.

Recommendations

Improve Chinese Semantic Dependency Parsing via Syntactic Dependency Parsing
IALP '12: Proceedings of the 2012 International Conference on Asian Language Processing

We address the problem of Chinese semantic dependency parsing. Dependency parsing is traditionally oriented to syntax analysis, which we denote by syntactic dependency parsing to distinguish it from semantic dependency parsing. In this paper, firstly we ...
Learning the scope of negation via shallow semantic parsing
COLING '10: Proceedings of the 23rd International Conference on Computational Linguistics

In this paper we present a simplified shallow semantic parsing approach to learning the scope of negation (SoN). This is done by formulating it as a shallow semantic parsing problem with the negation signal as the predicate and the negation scope as its ...
Joint syntactic and semantic parsing of Chinese
ACL '10: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

This paper explores joint syntactic and semantic parsing of Chinese to further improve the performance of both syntactic and semantic parsing, in particular the performance of semantic parsing (in this paper, semantic role labeling). This is done from ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

AAAI'19/IAAI'19/EAAI'19: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence

January 2019

10088 pages

ISBN:978-1-57735-809-1

Copyright © 2019 Association for the Advancement of Artificial Intelligence.

Sponsors

Association for the Advancement of Artificial Intelligence

Publisher

AAAI Press

Publication History

Published: 27 January 2019

Qualifiers

Research-article
Research
Refereed limited

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
50
Total Downloads

Downloads (Last 12 months)42
Downloads (Last 6 weeks)16

Reflects downloads up to 04 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Peretz GArraf MRadinsky KChen HDuh WHuang HKato MMothe JPoblete B(2023)What If: Generating Code to Answer Simulation Questions in Chemistry TextsProceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3539618.3591783(1335-1344)Online publication date: 19-Jul-2023
https://dl.acm.org/doi/10.1145/3539618.3591783
Yusuf IJiang LLo DRastogi ATufano RBavota GArnaoudova VHaiduc S(2022)Accurate generation of trigger-action programs with domain-adapted sequence-to-sequence learningProceedings of the 30th IEEE/ACM International Conference on Program Comprehension10.1145/3524610.3527922(99-110)Online publication date: 16-May-2022
https://dl.acm.org/doi/10.1145/3524610.3527922
Xu FVasilescu BNeubig G(2022)In-IDE Code Generation from Natural Language: Promise and ChallengesACM Transactions on Software Engineering and Methodology10.1145/348756931:2(1-47)Online publication date: 4-Mar-2022
https://dl.acm.org/doi/10.1145/3487569

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents