The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Lifelong and Continual Learning Dialogue Systems: Learning during Conversation
Open accessAbstract
Dialogue systems, also called chatbots, are now used in a wide range of applications. However, they still have some major weaknesses. One key weakness is that they are typically trained from manually-labeled data and/or written with handcrafted rules, and their knowledge bases (KBs) are also compiled by human experts. Due to the huge amount of manual effort involved, they are difficult to scale and also tend to produce many errors ought to their limited ability to understand natural language and the limited knowledge in their KBs. Thus, the level of user satisfactory is often low. In this paper, we propose to dramatically improve the situation by endowing the chatbots the ability to continually learn (1) new world knowledge, (2) new language expressions to ground them to actions, and (3) new conversational skills, during conversation by themselves so that as they chat more and more with users, they become more and more knowledgeable and are better and better able to understand diverse natural language expressions and to improve their conversational skills.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In practical applications like chatbots and agents, prompts are often much larger than generated responses such as summaries and code pieces, creating significant inference latency and memory utilization overhead.
“In practical applications like chatbots and agents, where prompts range from multi-turn conversations to extensive articles or codebases [1, 9, 10], prompts are often much larger than generated responses such as summaries and code pieces, thus creating significant inference latency and memory utilization overhead.”
From SnapKV: LLM Knows What You are Looking for Before Generation (2024) · cites this paper as [9]
The paper discusses chatbots using multi-turn dialogues (section “2. Coreference resolution”) and says response delays matter to users (section “Components of a LINC Framework”; page numbers unavailable). It does not establish that prompts are larger than generated responses or that prompt length causes inference-latency and memory overhead. (LLM, conf=0.84)
Experimental — accuracy not yet measured
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
Learning from Dialogue after Deployment: Feed Yourself, Chatbot!
Hancock, B., Bordes, A., Mazare, P.-E., & Weston, J. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1358 · Cited by 161
Naturalizing a Programming Language via Interactive Learning
Wang, S. I., Ginn, S., Liang, P., & Manning, C. D. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1086 · Cited by 59
Flagged first, then by citations
Research works printed but not linked: 26
- Andreas, J.; and Klein, D. 2015. Alignment-Based Compo- sitional Semantics for Instruction Following. In EMNLP.
- Artzi, Y.; and Zettlemoyer, L. 2013. Weakly supervised learning of semantic parsers for mapping instructions to ac- tions. TACL .
- Chen, Z.; and Liu, B. 2014. Topic modeling using top- ics from many domains, lifelong learning and big data. In ICML.
- Forbes, M.; Rao, R. P.; Zettlemoyer, L.; and Cakmak, M. 2015. Robot programming by demonstration with situated spatial language understanding. In ICRA.
- Li, J.; Monroe, W.; Ritter, A.; Jurafsky, D.; Galley, M.; and Gao, J. 2016. Deep Reinforcement Learning for Dialogue Generation. In EMNLP.
- Liu, B. 2020. Learning on the Job: Online Lifelong and Continual Learning. In AAAI.
- Liu, B.; and Mei, C. 2020. Lifelong Knowledge Learning in Rule-based Dialogue Systems. arXiv:2011.09811 [cs.AI] . · arXiv
- Liu, Q.; Chen, Y.; Chen, B.; Lou, J.-G.; Chen, Z.; Zhou, B.; and Zhang, D. 2020. You impress me: Dialogue generation via mutual persona perception. In ACL.
- Luo, L.; Huang, W.; Zeng, Q.; Nie, Z.; and Sun, X. 2019. Learning personalized end-to-end goal-oriented dialog. In AAAI.
- Mazumder, S.; Liu, B.; Ma, N.; and Wang, S. 2020a. Contin- uous and Interactive Factual Knowledge Learning in Verifi- cation Dialogues. NeurIPS-2020 Workshop on Human And Machine in-the-Loop Evaluation and Learning Strategies .
- Mazumder, S.; Liu, B.; Wang, S.; and Esmaeilpour, S. 2020b. An Application-Independent Approach to Building Task-Oriented Chatbots with Interactive Continual Learn- ing. NeurIPS-2020 Workshop on Human in the Loop Di- alogue Systems .
- Misra, D.; Langford, J.; and Artzi, Y. 2017. Mapping In- structions and Visual Observations to Actions with Rein- forcement Learning. In EMNLP.
- Pamungkas, E. W. 2019. Emotionally-aware chatbots: A sur- vey. arXiv preprint arXiv:1906.09774 . · arXiv
- Ruvolo, P.; and Eaton, E. 2013. ELLA: An efficient lifelong learning algorithm. In ICML.
- Serban, I. V.; Sordoni, A.; Bengio, Y.; Courville, A.; and Pineau, J. 2016. Building end-to-end dialogue systems using generative hierarchical neural network models. In AAAI.
- Shang, L.; Lu, Z.; and Li, H. 2015. Neural Responding Ma- chine for Short-Text Conversation. In ACL-IJCNLP.
- Shuster, K.; Urbanek, J.; Dinan, E.; Szlam, A.; and Weston, J. 2020. Deploying Lifelong Open-Domain Dialogue Learn- ing. arXiv preprint arXiv:2008.08076 . · arXiv
- Silver, D. L.; Yang, Q.; and Li, L. 2013. Lifelong machine learning systems: Beyond learning algorithms. In 2013 AAAI spring symposium series.
- Tellex, S.; Gopalan, N.; Kress-Gazit, H.; and Matuszek, C. 2020. Robots that use language. Annual Review of Control, Robotics, and Autonomous Systems .
- Thrun, S. 1998. Lifelong learning algorithms. In Learning to learn. Springer.
- Vinyals, O.; and Le, Q. 2015. A neural conversational model. arXiv preprint arXiv:1506.05869 . · arXiv
- Vogel, A.; and Jurafsky, D. 2010. Learning to follow navi- gational directions. In ACL.
- Wen, T.-H.; Vandyke, D.; Mrkšić, N.; Gasic, M.; Bara- hona, L. M. R.; Su, P.-H.; Ultes, S.; and Young, S. 2017. A Network-based End-to-End Trainable Task-oriented Dia- logue System. In EACL.
- Young, T.; Cambria, E.; Chaturvedi, I.; Zhou, H.; Biswas, S.; and Huang, M. 2018. Augmenting end-to-end dialogue systems with commonsense knowledge. In AAAI.
- Zhou, H.; Huang, M.; Zhang, T.; Zhu, X.; and Liu, B. 2018a. Emotional chatting machine: Emotional conversation gener- ation with internal and external memory. In AAAI.
- Zhou, H.; Young, T.; Huang, M.; Zhao, H.; Xu, J.; and Zhu, X. 2018b. Commonsense knowledge aware conversation generation with graph attention. In IJCAI.
Cited by
Sorted by citations
A Comprehensive Survey of Continual Learning: Theory, Method and Application
Wang, L., Zhang, X., Su, H., & Zhu, J. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3367329 · Cited by 1,113
An Intelligent Virtual Standard Patient for Medical Students Training Based on Oral Knowledge Graph
Song, W., Hou, X., Li, S., Chen, C., Gao, D., Wang, X., Sun, Y., Hou, J., & Hao, A. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3205456 · Cited by 18
SnapKV: LLM Knows What You are Looking for Before Generation
Li, Y., Huang, Y., Yang, B., Venkitesh, B., Locatelli, A., Ye, H., Cai, T., Lewis, P., & Chen, D. (2024) · arXiv · doi:10.48550/arxiv.2404.14469 · Cited by 74
“In practical applications such as chatbots and agents, where inputs can be multi-turn conversations, extensive articles or codebases [1, 9, 10], input sizes are often much larger than the sizes of generated responses, resulting in significant overhead.”
Background
Metadata
- Authors
- Liu, B., & Mazumder, S.
- Affiliations
- University of Illinois Chicago (US)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2021-05-18
- Volume
- 35
- Issue
- 17
- Pages
- 15058-15063
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W3176617324
- Cited by
- 34
- References
- 2
- Citations by year
- 2025: 6 · 2024: 7 · 2023: 10 · 2022: 7 · 2021: 3
- FWCI
- 3.01
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1838770, 1910424)
- Northrop Grumman
- Defense Advanced Research Projects Agency (HR001120C0023)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Keywords
- dialogue systems, chatbots, continual learning, lifelong learning, knowledge base updating, natural language understanding, conversation skills
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
