Abstract
Task-oriented virtual assistants are software systems that provide users with a natural language interface to complete domain-specific tasks. With the recent technological advances in natural language processing and machine learning, an increasing number of task-oriented virtual assistants have been developed. However, due to the well-known complexity and difficulties of the natural language understanding problem, it is challenging to manage a task-oriented virtual assistant software project. Meanwhile, the management and experience related to the development of virtual assistants are hardly studied or shared in the research community or industry, to the best of our knowledge. To bridge this knowledge gap, in this paper, we share our experience and the lessons that we have learned at managing a task-oriented virtual assistant software project at Microsoft. We believe that our practices and the lessons learned can provide a useful reference for other researchers and practitioners who aim to develop a virtual assistant system. Finally, we have developed a requirement management tool, named SpecSpace, which can facilitate the management of virtual assistant projects.
摘要
面向任务的虚拟助手是为用户提供自然语言接口以完成特定领域任务的软件系统。随着近年来自然语言处理和机器学习技术的发展, 越来越多面向任务的虚拟助手产品开始涌现。由于自然语言理解这一问题的复杂性和困难性, 管理一个面向任务的虚拟助手软件项目具有挑战性。同时, 据我们所知, 与虚拟助手开发相关的管理和经验在学术界和工业界都少有研究或分享。为填补这空白, 本文分享了我们在微软开发一项虚拟助手产品过程中的管理经验和教训。相信我们的经验和教训能为研究人员和相关从业者提供宝贵参考。最后, 设计了一个需求管理工具SpecSpace, 对我们虚拟助手项目的管理有很大帮助。
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Amershi S, Begel A, Bird C, et al., 2019. Software engineering for machine learning: a case study. Proc IEEE/ACM 41st Int Conf on Software Engineering: Software Engineering in Practice, p.291–300. https://doi.org/10.1109/ICSE-SEIP.2019.00042
Arpteg A, Brinne B, Crnkovic-Friis L, et al., 2018. Software engineering challenges of deep learning. Proc 44th Euromicro Conf on Software Engineering and Advanced Applications, p.50–59. https://doi.org/10.1109/SEAA.2018.00018
Bender EM, Koller A, 2020. Climbing towards NLU: on meaning, form, and understanding in the age of data. Proc 58th Annual Meeting of the Association for Computational Linguistics, p.5185–5198. https://doi.org/10.18653/v1/2020.acl-main.463
Bonwell CC, Eison JA, 1991. Active Learning: Creating Excitement in the Classroom. ERIC Number ED336049. The George Washington University, Washington, USA.
Bradley AJ, 2020. Brace Yourself for an Explosion of Virtual Assistants. https://blogs.gartner.com/anthony_bradley/2020/08/10/brace-yourself-for-an-explosion-of-virtual-assistants/ [Accessed on Aug. 10, 2020].
Breck E, Cai SQ, Nielsen E, et al., 2017. The ML test score: a rubric for ML production readiness and technical debt reduction. Proc IEEE Int Conf on Big Data, p.1123–1132. https://doi.org/10.1109/BigData.2017.8258038
Campagna G, Xu SL, Moradshahi M, et al., 2019. Genie: a generator of natural language semantic parsers for virtual assistant commands. Proc 40th ACM SIGPLAN Conf on Programming Language Design and Implementation, p.394–410. https://doi.org/10.1145/3314221.3314594
Dhamdhere K, McCurley KS, Nahmias R, et al., 2017. Analyza: exploring data with conversation. Proc 22nd Int Conf on Intelligent User Interfaces, p.493–504. https://doi.org/10.1145/3025171.3025227
Facebook, 2020. Surveybot. https://surveybot.io/ [Accessed on Aug. 10, 2020].
Gao Y, Lou JG, Zhang DM, 2019. A hybrid semantic parsing approach for tabular data analysis. https://arxiv.org/abs/1910.10363
Hains G, Jakobsson A, Khmelevsky Y, 2018. Towards formal methods and software engineering for deep learning: security, safety and productivity for DL systems development. Proc Annual IEEE Int Systems Conf, p.1–5. https://doi.org/10.1109/SYSCON.2018.8369576
Horkoff J, 2019. Non-functional requirements for machine learning: challenges and new directions. Proc 27th Int Requirements Engineering Conf, p.386–391. https://doi.org/10.1109/RE.2019.00050
Huang XW, Kroening D, Kwiatkowska M, et al., 2018. Safety and trustworthiness of deep neural networks: a survey. https://arxiv.org/abs/1812.08342v1
Islam J, Nguyen HA, Pan R, et al., 2019. What do developers ask about ML libraries? A large-scale study using stack overflow. https://arxiv.org/abs/1906.11940
Krishnan S, Wang JN, Wu E, et al., 2016. ActiveClean: interactive data cleaning for statistical modeling. Proc VLDB Endow, 9(12):948–959. https://doi.org/10.14778/2994509.2994514
Krishnan S, Franklin MJ, Goldberg K, et al., 2017. Boost-Clean: automated error detection and repair for machine learning. https://arxiv.org/abs/1711.01299
Lee DTS, Zhou ZQ, Tse TH, 2020. Metamorphic robustness testing of Google Translate. Proc 42nd Int Conf on Software Engineering Workshops, p.388–395. https://doi.org/10.1145/3387940.3391484
Marijan D, Gotlieb A, Ahuja MK, 2019. Challenges of testing machine learning based systems. Proc IEEE Int Conf on Artificial Intelligence Testing, p.101–102. https://doi.org/10.1109/AITest.2019.00010
Mason L, Baxter J, Bartlett PL, et al., 1999. Boosting algorithms as gradient descent. Proc 12th Int Conf on Neural Information Processing Systems, p.512–518.
Masuda S, Ono K, Yasue T, et al., 2018. A survey of software quality for machine learning applications. IEEE Int Conf on Software Testing, Verification and Validation Workshops, p.279–284. https://doi.org/10.1109/ICSTW.2018.00061
Microsoft, 2020. Power BI. https://powerbi.microsoft.com/ [Accessed on Aug. 10, 2020].
Oram R, 2019. Meeting Edward: Chatbots and the Changing Face of the Hotel Guest Experience. https://blogs.oracle.com/hospitality/chatbots-and-the-changing-the-face-of-the-hotel-guest-experience [Accessed on Aug. 10, 2020].
Polyzotis N, Roy S, Whang SE, et al., 2018. Data lifecycle challenges in production machine learning: a survey. ACM SIGMOD Rec, 47(2):17–28. https://doi.org/10.1145/3299887.3299891
Radford A, Wu J, Child R, et al., 2019. Language Models are Unsupervised Multitask Learners. https://openai.com/blog/ [Accessed on Jan. 1, 2020].
Schapire RE, 1990. The strength of weak learnability. Mach Learn, 5(2):197–227. https://doi.org/10.1007/BF00116037
Schelter S, Lange D, Schmidt P, et al., 2018a. Automating large-scale data quality verification. Proc VLDB Endow, 11(12):1781–1794. https://doi.org/10.14778/3229863.3229867
Schelter S, Biessmann F, Januschowski T, et al., 2018b. On challenges in machine learning model management. IEEE Data Eng Bull, 41(4):5–15.
Sculley D, Holt G, Golovin D, et al., 2015. Hidden technical debt in machine learning systems. Proc 28th Int Conf on Neural Information Processing Systems, p.2503–2511.
Sun NY, Yang XF, Liu YF, 2020. TableQA: a large-scale Chinese text-to-SQL dataset for table-aware SQL generation. https://arxiv.org/abs/2006.06434v1
Tableau, 2020a. Ask Data. https://www.tableau.com/products/new-features/ask-data/ [Accessed on Aug. 10, 2020].
Tableau, 2020b. Tableau. https://www.tableau.com/ [Accessed on Aug. 10, 2020].
Task Virtual, 2020. TaskVirtual. https://taskvirtual.com/ [Accessed on Aug. 10, 2020].
Thrun S, 1998. Lifelong learning algorithms. In: Thrun S, Pratt L (Eds.), Learning to Learn. Kluwer Academic Publishers, Norwell, USA, p.181–209.
Vogelsang A, Borg M, 2019. Requirements engineering for machine learning: perspectives from data scientists. Proc 27th Int Requirements Engineering Conf Workshops, p.245–251. https://doi.org/10.1109/REW.2019.00050
Voigt P, von dem Bussche A, 2017. The EU General Data Protection Regulation (GDPR): a Practical Guide. Springer, Cham, Germany. https://doi.org/10.1007/978-3-319-57959-7
Wikipedia, 2021. Virtual Assistant. https://en.wikipedia.org/wiki/Virtual_assistant [Accessed on Aug. 10, 2020].
Yao ZY, Su Y, Sun H, et al., 2019. Model-based interactive semantic parsing: a unified framework and a text-to-SQL case study. Proc Conf on Empirical Methods in Natural Language Processing and the 9th Int Joint Conf on Natural Language Processing, p.5447–5458. https://doi.org/10.18653/v1/D19-1547
Young SWH, 2014. Improving library user experience with A/B testing: principles and process. Weave J Libr User Exper. https://doi.org/10.3998/weave.12535642.0001.101
Zhang JM, Harman M, Ma L, et al., 2022. Machine learning testing: survey, landscapes and horizons. IEEE Trans Softw Eng, 48(1):1–36. https://doi.org/10.1109/TSE.2019.2962027
Zhang TY, Gao CY, Ma L, et al., 2019. An empirical study of common challenges in developing deep learning applications. Proc 30th Int Symp on Software Reliability Engineering, p.104–115. https://doi.org/10.1109/ISSRE.2019.00020
Zhong V, Xiong CM, Socher R, 2017. Seq2SQL: generating structured queries from natural language using reinforcement learning. https://arxiv.org/abs/1709.00103v5
Acknowledgements
This work is supported by Microsoft Research Asia and is done during the internships of Shuyue LI and Jiaqi GUO.
Author information
Authors and Affiliations
Contributions
Shuyue LI, Jiaqi GUO, Jianguang LOU, and Ting LIU designed the research. Yan GAO, Dejian YANG, and Yan XIAO developed XTalk and provided the data. Shuyue LI, Jiaqi GUO, Yan GAO, and Ting LIU drafted the paper. Yadong ZHOU helped organize the paper. Jianguang LOU and Ting LIU revised and finalized the paper.
Corresponding author
Additional information
Compliance with ethics guidelines
Shuyue LI, Jiaqi GUO, Yan GAO, Jianguang LOU, Dejian YANG, Yan XIAO, Yadong ZHOU, and Ting LIU declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Li, S., Guo, J., Gao, Y. et al. How to manage a task-oriented virtual assistant software project: an experience report. Front Inform Technol Electron Eng 23, 749–762 (2022). https://doi.org/10.1631/FITEE.2100467
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/FITEE.2100467