AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Computer Science and Technology Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Survey

Knowledge-Enhanced Conversational Agents

LINKS Foundation, 10138 Turin, Italy
Show Author Information

Abstract

Humanity has fantasized about artificial intelligence tools able to discuss with human beings fluently for decades. Numerous efforts have been proposed ranging from ELIZA to the modern vocal assistants. Despite the large interest in this research and innovation field, there is a lack of common understanding on the concept of conversational agents and general over expectations that hide the current limitations of existing solutions. This work proposes a literature review on the subject with a focus on the most promising type of conversational agents that are powered on top of knowledge bases and that can offer the ground knowledge to hold conversation autonomously on different topics. We describe a conceptual architecture to define the knowledge-enhanced conversational agents and investigate different domains of applications. We conclude this work by listing some promising research pathways for future work.

Keywords

conversational agentdialogue systemknowledge enhancingartificial agentintelligent conversation

Electronic Supplementary Material

Download File(s)
JCST-2210-12883-Highlights.pdf (277.2 KB)

References

[1]
Mayor A. Gods and Robots. Princeton University Press, 2018.
Crossref
[2]

Weizenbaum J. ELIZA—A computer program for the study of natural language communication between man and machine. Communications of the ACM, 1966, 9(1): 36–45. DOI: 10.1145/365153.365168.
Crossref Google Scholar
[3]
Hofstadter D R. Preface 4 The ineradicable Eliza effect and its dangers, epilogue. In Fluid Concepts and Creative Analogies: Computer Models of the Fundamental Mechanisms of Thought, Hofstadter D R (ed.), Basic Books, Inc., 1996, p.157.
[4]
Brown T B, Mann B, Ryder N et al. Language models are few-shot learners. In Proc. the 34th Int. Conf. Neural Information Processing Systems, Dec. 2020, Article No. 159.
[5]
Ouyang L, Wu J, Jiang X et al. Training language models to follow instructions with human feedback. In Proc. the 36th Int. Conf. Neural Information Processing Systems, Nov. 2022, Article No. 2011.
[6]
Kovács B. The Turing test of online reviews: Can we tell the difference between human-written and GPT-4-written online reviews? Marketing Letters, 2024. DOI: 10.1007/s11002-024-09729-3.
Crossref
[7]
Bender E M, Gebru T, McMillan-Major A, Shmitchell S. On the dangers of stochastic parrots: Can language models be too big? In Proc. the 2021 ACM Conference on Fairness, Accountability, and Transparency, Mar. 2021, pp.610–623. DOI: 10.1145/3442188.3445922.
Crossref
[8]
Hendrycks D, Burns C, Basart S, Zou A, Mazeika M, Song D, Steinhardt J. Measuring massive multitask language understanding. arXiv: 2009.03300, 2021. https://arxiv.org/abs/2009.03300, May 2024.
[9]
Zhang Y, Li Y F, Cui L Y et al. Siren’s song in the AI ocean: A survey on hallucination in large language models. arXiv: 2309.01219, 2023. https://arxiv.org/abs/2309.01219, May 2024.
[10]
Kandpal N, Deng H K, Roberts A, Wallace E, Raffel C. Large language models struggle to learn long-tail knowledge. In Proc. the 40th International Conference on Machine Learning, Jul. 2023, pp.15696–15707.
[11]

Singhal K, Azizi S, Tu T et al. Large language models encode clinical knowledge. Nature, 2023, 620(7972): 172–180. DOI: 10.1038/s41586-023-06291-2.
Crossref Google Scholar
[12]
Eggins S, Slade D. Analysing Casual Conversation. Equinox, 2004.
[13]
Lewis P, Perez E, Piktus A et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Proc. the 34th International Conference on Neural Information Processing Systems, Dec. 2020, Article No.793.
[14]

Yang L F, Chen H Y, Li Z, Ding X, Wu X D. Give us the facts: Enhancing large language models with knowledge graphs for fact-aware language modeling. IEEE Trans. Knowledge and Data Engineering, 2024, 36(7): 3091–3110. DOI: 10.1109/TKDE.2024.3360454.
Crossref Google Scholar
[15]

Syvänen S, Valentini C. Conversational agents in online organization–stakeholder interactions: A state-of-the-art analysis and implications for further research. Journal of Communication Management, 2020, 24(4): 339–362. DOI: 10.1108/JCOM-11-2019-0145.
Crossref Google Scholar
[16]
Ram A, Prasad R, Khatri C et al. Conversational AI: The science behind the Alexa prize. arXiv: 1801.03604, 2018. https://arxiv.org/abs/1801.03604, May 2024.
[17]

Chen H S, Liu X R, Yin D W, Tang J L. A survey on dialogue systems: Recent advances and new frontiers. ACM SIGKDD Explorations Newsletter, 2017, 19(2): 25–35. DOI: 10.1145/3166054.3166058.
Crossref Google Scholar
[18]

Huang M L, Zhu X Y, Gao J F. Challenges in building intelligent open-domain dialog systems. ACM Trans. Information Systems, 2020, 38(3): Article No. 21. DOI: 10.1145/3383123.
Crossref Google Scholar
[19]
Hussain S, Ameri Sianaki O, Ababneh N. A survey on conversational agents/chatbots classification and design techniques. In Proc. the 33rd Int. Conf. Advanced Information Networking and Applications, Mar. 2019, pp.946–956. DOI: 10.1007/978-3-030-15035-8_93.
Crossref
[20]

de Barcelos Silva A, Gomes M M, da Costa C A, da Rosa Righi R, Barbosa J L V, Pessin G, De Doncker G, Federizzi G. Intelligent personal assistants: A systematic literature review. Expert Systems with Applications, 2020, 147: 113193. DOI: 10.1016/j.eswa.2020.113193.
Crossref Google Scholar
[21]
Gemini Team. Gemini: A family of highly capable multimodal models. arXiv: 2312.11805, 2023. https://arxiv.org/abs/2312.11805, May 2024.
[22]
Bao S Q, He H, Wang F, Wu H, Wang H F, Wu W Q, Guo Z, Liu Z B, Xu X C. PLATO-2: Towards building an open-domain chatbot via curriculum learning. In Proc. the 2021 Findings of the Association for Computational Linguistics, Aug. 2021, pp.2513–2525. DOI: 10.18653/v1/2021.findings-acl.222.
Crossref
[23]
Adiwardana D, Luong M T, So D R, Hall J, Fiedel N, Thoppilan R, Yang Z, Kulshreshtha A, Nemade G, Lu Y F, Le Q V. Towards a human-like open-domain chatbot. arXiv: 2001.09977, 2020. https://arxiv.org/abs/2001.09977, May 2024.
[24]
Papaioannou I, Cercas Curry A, Part J et al. Alana: Social dialogue using an ensemble model and a ranker trained on user feedback. In Proc. the 2017 Alexa Prize, Aug. 2017.
[25]

Ferrara E, Varol O, Davis C, Menczer F, Flammini A. The rise of social bots. Communications of the ACM, 2016, 59(7): 96–104. DOI: 10.1145/2818717.
Crossref Google Scholar
[26]

Subrahmanian V S, Azaria A, Durst S, Kagan V, Galstyan A, Lerman K, Zhu L H, Ferrara E, Flammini A, Menczer F. The DARPA twitter bot challenge. Computer, 2016, 49(6): 38–46. DOI: 10.1109/MC.2016.183.
Crossref Google Scholar
[27]
Roller S, Dinan E, Goyal N et al. Recipes for building an open-domain chatbot. In Proc. the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, Apr. 2021, pp.300–325. DOI: 10.18653/v1/2021.eacl-main.24.
Crossref
[28]
Sun H T, Dhingra B, Zaheer M et al. Open domain question answering using early fusion of knowledge bases and text. In Proc. the 2018 Conference on Empirical Methods in Natural Language Processing, Oct. 31-Nov. 1, 2018, pp.4231–4242. DOI: 10.18653/v1/D18-1455.
Crossref
[29]
Porcheron M, Fischer J E, Reeves S, Sharples S. Voice interfaces in everyday life. In Proc. the 2018 CHI Conference on Human Factors in Computing Systems, Apr. 2018, Article No. 640. DOI: 10.1145/3173574.3174214.
Crossref
[30]
Pieraccini R. The Voice in the Machine: Building Computers that Understand Speech. MIT Press, 2012.
Crossref
[31]
Sharma S, Brennan J, Nurse J. StockBabble: A conversational financial agent to support stock market investors. In Proc. the 3rd Conference on Conversational User Interfaces, Jul. 2021, Article No. 25. DOI: 10.1145/3469595.3469620.
Crossref
[32]
Fraser J, Papaioannou I, Lemon O. Spoken conversational AI in video games: Emotional dialogue management increases user engagement. In Proc. the 18th International Conference on Intelligent Virtual Agents, Nov. 2018, pp.179–184. DOI: 10.1145/3267851.3267896.
Crossref
[33]
McTear M, Callejas Z, Griol D. The Conversational Interface: Talking to Smart Devices. Springer, 2016. DOI: 10.1007/978-3-319-32967-3.
Crossref
[34]

Sarikaya R. The technology behind personal digital assistants: An overview of the system architecture and key components. IEEE Signal Processing Magazine, 2017, 34(1): 67–81. DOI: 10.1109/MSP.2016.2617341.
Crossref Google Scholar
[35]
Swartout W R, Nye B D, Hartholt A et al. Designing a personal assistant for life-long learning (PAL3). In Proc. the 29th International Florida Artificial Intelligence Research Society Conference, May 2016, pp.491–496.
[36]
Cicció J A, Quesada L. Framework for creating audio games for intelligent personal assistants. In Proc. the 2017 International Conference on Advances in Human Factors and Wearable Technologies, July 2017, pp.204–214. DOI: 10.1007/978-3-319-60639-2_21.
Crossref
[37]
McTear M. Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots. Springer, 2020: 1–251. DOI: 10.1007/978-3-031-02176-3.
Crossref
[38]

Minsky M. Society of mind: A response to four reviews. Artificial Intelligence, 1991, 48(3): 371–396. DOI: 10.1016/ 0004-3702(91)90036-J.
Crossref Google Scholar
[39]
Marková I, Linell P, Grossen M, Salazar Orvig A. Dialogue in Focus Groups: Exploring Socially Shared Knowledge. Equinox Publishing, 2007.
[40]
Kim S, Eric M, Hedayatnia B, Gopalakrishnan K, Liu Y, Huang C W, Hakkani-Tur D. Beyond domain APIs: Task-oriented conversational modeling with unstructured knowledge access track in DSTC9. arXiv: 2101.09276, 2021. https://arxiv.org/abs/2101.09276, May 2024.
[41]
Chen Q, Zhuo Z, Wang W. BERT for joint intent classification and slot filling. arXiv: 1902.10909, 2019. https://arxiv.org/abs/1902.10909, May 2024.
[42]
Castellucci G, Bellomaria V, Favalli A, Romagnoli R. Multi-lingual intent detection and slot filling in a joint BERT-based model. arXiv: 1907.02884, 2019. https://arxiv.org/abs/1907.02884, May 2024.
[43]
Wang J X, Wei K, Radfar M, Zhang W W, Chung C. Encoding syntactic knowledge in transformer encoder for intent detection and slot filling. In Proc. the 35th AAAI Conference on Artificial Intelligence, Feb. 2021, pp.13943–13951. DOI: 10.1609/aaai.v35i16.17642.
Crossref
[44]
Zhang J G, Hashimoto K, Wu C S, Wang Y, Yu P, Socher R, Xiong C M. Find or classify? Dual strategy for slot-value predictions on multi-domain dialog state tracking. In Proc. the 9th Joint Conference on Lexical and Computational Semantics, Dec. 2020, pp.154–167.
[45]
Gao S Y, Sethi A, Agarwal S, Chung T, Hakkani-Tür D Z. Dialog state tracking: A neural reading comprehension approach. In Proc. the 20th Annual SIGdial Meeting on Discourse and Dialogue, Sept. 2019, pp.264–273. DOI: 10.18653/v1/W19-5932.
Crossref
[46]
Zhou L, Small K. Multi-domain dialogue state tracking as dynamic knowledge graph enhanced question answering. arXiv: 1911.06192, 2019. https://arxiv.org/abs/1911.06192, May 2024.
[47]

Rohmatillah M, Chien J T. Advances and challenges in multi-domain task-oriented dialogue policy optimization. APSIPA Trans. Signal and Information Processing, 2023, 12(1): e37. DOI: 10.1561/116.00000132.
Crossref Google Scholar
[48]
Peng B L, Zhu C G, Li C Y, Li X J, Li J C, Zeng M, Gao J F. Few-shot natural language generation for task-oriented dialog. arXiv: 2002.12328, 2020. https://arxiv.org/abs/2002.12328, May 2024.
Crossref
[49]

Richards B A, Lillicrap T P. Dendritic solutions to the credit assignment problem. Current Opinion in Neurobiology, 2019, 54: 28–36. DOI: 10.1016/j.conb.2018.08.003.
Crossref Google Scholar
[50]
Gao J F, Galley M, Li L H. Neural approaches to conversational AI. In Proc. the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, Jul. 2018, pp.1371–1374. DOI: 10.1145/3209978.3210183.
Crossref
[51]
Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks. In Proc. the 27th International Conference on Neural Information Processing Systems, Dec. 2014, pp.3104–3112.
[52]
Clark K, Luong M T, Le Q V, Manning C D. ELECTRA: Pre-training text encoders as discriminators rather than generators. arXiv: 2003.10555, 2020. https://arxiv.org/abs/2003.10555, May 2024.
[53]
Song K T, Tan X, Qin T, Lu J F, Liu T Y. MPNet: Masked and permuted pre-training for language understanding. In Proc. the 34th Int. Conf. Neural Information Processing Systems, Dec. 2020, Article No.1414.
[54]
Gao T Y, Yao X C, Chen D Q. SimCSE: Simple contrastive learning of sentence embeddings. In Proc. the 2021 Conference on Empirical Methods in Natural Language Processing, Nov. 2021, pp.6894–6910. DOI: 10.18653/v1/2021.emnlp-main.552.
Crossref
[55]

Chowdhery A, Narang S, Devlin J et al. PaLM: Scaling language modeling with pathways. The Journal of Machine Learning Research, 2022, 24(1): 240.
Google Scholar
[56]
Petroni F, Rocktäschel T, Riedel S, Lewis P, Bakhtin A, Wu Y X, Miller A. Language models as knowledge bases? In Proc. the 2019 EMNLP-IJCNLP, Nov. 2019, pp.2463–2473. DOI: 10.18653/v1/D19-1250.
Crossref
[57]
Taylor R, Kardas M, Cucurull G, Scialom T, Hartshorn A, Saravia E, Poulton A, Kerkez V, Stojnic R. Galactica: A large language model for science. arXiv: 2211.09085, 2022. https://arxiv.org/abs/2211.09085, May 2024.
[58]

Yu W H, Zhu C G, Li Z T, Hu Z T, Wang Q Y, Ji H, Jiang M. A survey of knowledge-enhanced text generation. ACM Computing Surveys, 2022, 54(11s): 227. DOI: 10.1145/3512467.
Crossref Google Scholar
[59]

Adamopoulou E, Moussiades L. Chatbots: History, technology, and applications. Machine Learning with Applications, 2020, 2: 100006. DOI: 10.1016/j.mlwa.2020.100006.
Crossref Google Scholar
[60]
Huang T H, Chang J C, Bigham J P. Evorus: A crowd-powered conversational assistant built to automate itself over time. In Proc. the 2018 CHI Conference on Human Factors in Computing Systems, Apr. 2018, Article No.295. DOI: 10.1145/3173574.3173869.
Crossref
[61]
Liu D Y H, Yan Y, Gong Y Y et al. GLGE: A new general language generation evaluation benchmark. In Proc. the 2021 Findings of the Association for Computational Linguistics, Aug. 2021, pp.408–420. DOI: 10.18653/v1/2021.findings-acl.36.
Crossref
[62]

Ji S X, Pan S R, Cambria E, Marttinen P, Yu P S. A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Trans. Neural Networks and Learning Systems, 2022, 33(2): 494–514. DOI: 10.1109/TNNLS.2021.3070843.
Crossref Google Scholar
[63]
Young T, Cambria E, Chaturvedi I, Zhou H, Biswas S, Huang M L. Augmenting end-to-end dialogue systems with commonsense knowledge. In Proc. the 32nd AAAI Conference on Artificial Intelligence, Feb. 2018, pp.4970–4977. DOI: 10.1609/aaai.v32i1.11923.
Crossref
[64]
Zhang H Y, Liu Z H, Xiong C Y, Liu Z Y. Grounded conversation generation as guided traverses in commonsense knowledge graphs. In Proc. the 58th Annual Meeting of the Association for Computational Linguistics, Jul. 2020, pp.2031–2043. DOI: 10.18653/v1/2020.acl-main.184.
Crossref
[65]
Yang S Q, Zhang R, Erfani S. GraphDialog: Integrating graph knowledge into end-to-end task-oriented dialogue systems. In Proc. the 2020 EMNLP, Nov. 2020, pp.1878–1888. DOI: 10.18653/v1/2020.emnlp-main.147.
Crossref
[66]
Ghazvininejad M, Brockett C, Chang M W, Dolan B, Gao J F, Yih W T, Galley M. A knowledge-grounded neural conversation model. In Proc. the 32nd AAAI Conference on Artificial Intelligence, Feb. 2018, pp.5110–5117. DOI: 10.1609/aaai.v32i1.11977.
Crossref
[67]
Weston J, Chopra S, Bordes A. Memory networks. arXiv: 1410.3916, 2015. https://arxiv.org/abs/1410.3916, May 2024.
[68]
Sukhbaatar S, Szlam A, Weston J et al. End-to-end memory networks. In Proc. the 28th Int. Conf. Neural Information Processing Systems, Dec. 2015, pp.2440–2448.
[69]
Miller A, Fisch A, Dodge J, Karimi A H, Bordes A, Weston J. Key-value memory networks for directly reading documents. In Proc. the 2016 Conference on Empirical Methods in Natural Language Processing, Nov. 2016, pp.1400–1409. DOI: 10.18653/v1/D16-1147.
Crossref
[70]
Vougiouklis P, Hare J, Simperl E. A neural network approach for knowledge-driven response generation. In Proc. the 26th Int. Conf. Computational Linguistics: Technical Papers, Dec. 2016, pp.3370–3380.
[71]
Madotto A, Wu C S, Fung P. Mem2Seq: Effectively incorporating knowledge bases into end-to-end task-oriented dialog systems. In Proc. the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1), Jul. 2018, pp.1468–1478. DOI: 10.18653/v1/P18-1136.
Crossref
[72]
Gangi Reddy R, Contractor D, Raghu D, Joshi S. Multi-level memory for task oriented dialogs. In Proc. the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (Volume 1), Jun. 2019, pp.3744–3754. DOI: 10.18653/v1/N19-1375.
Crossref
[73]

Wen J T, Jiang D Z, Tu G, Liu C, Cambria E. Dynamic interactive multiview memory network for emotion recognition in conversation. Information Fusion, 2023, 91: 123–133. DOI: 10.1016/j.inffus.2022.10.009.
Crossref Google Scholar
[74]

Zhang Z, Takanobu R, Zhu Q, Huang M L, Zhu X Y. Recent advances and challenges in task-oriented dialog systems. Science China Technological Sciences, 2020, 63(10): 2011–2027. DOI: 10.1007/s11431-020-1692-3.
Crossref Google Scholar
[75]
Koncel-Kedziorski R, Bekal D, Luan Y et al. Text generation from knowledge graphs with graph transformers. In Proc. the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (Volume 1), Jun. 2019, pp.2284–2293. DOI: 10.18653/v1/N19-1238.
Crossref
[76]
Fu Y, Feng Y S. Natural answer generation with heterogeneous memory. In Proc. the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (Volume 1), Jun. 2018, pp.185–195. DOI: 10.18653/v1/N18-1017.
Crossref
[77]
Mi H T, Ren Q Y, Dai Y P, He Y F, Sun J, Li Y B, Zheng J, Xu P. Towards generalized models for beyond domain API task-oriented dialogue. In Proc. the 2021 AAAI-21 DSTC9 Workshop, Feb. 2021.
[78]

He H, Lu H, Bao S Q, Wang F, Wu H, Niu Z Y, Wang H F. Learning to select external knowledge with multi-scale negative sampling. IEEE/ACM Trans. Audio, Speech, and Language Processing, 2024, 32: 714–720. DOI: 10.1109/TASLP.2023.3301222.
Crossref Google Scholar
[79]
Jin D, Gao S Y, Kim S, Liu Y, Hakkani-Tur D. Towards zero and few-shot knowledge-seeking turn detection in task-orientated dialogue systems. In Proc. the 3rd Workshop on Natural Language Processing for Conversational AI, Nov. 2021, pp.281–288. DOI: 10.18653/v1/2021.nlp4convai-1.27.
Crossref
[80]
Tan C H, Yang X Y, Zheng Z O, Li T D, Feng Y F, Gu J C, Liu Q, Liu D, Ling Z H, Zhu X D. Learning to retrieve entity-aware knowledge and generate responses with copy mechanism for task-oriented dialogue systems. arXiv: 2012.11937, 2020. https://arxiv.org/abs/2012.11937, May 2024.
[81]
Wang Y L, Li P, Sun M S, Liu Y. Self-knowledge guided retrieval augmentation for large language models. In Proc. the 2023 Findings of the Association for Computational Linguistics, Dec. 2023, pp.10303–10315. DOI: 10.18653/v1/2023.findings-emnlp.691.
Crossref
[82]
Liu Z Y, Lin Y K, Sun M S. Representation Learning for Natural Language Processing. Springer, 2020. DOI: 10.1007/978-981-15-5573-2.
Crossref
[83]
Karpukhin V, Oguz B, Min S, Lewis P, Wu L, Edunov S, Chen D Q, Yih W T. Dense passage retrieval for open-domain question answering. In Proc. the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov. 2020, pp.6769–6781. DOI: 10.18653/v1/2020.emnlp-main.550.
Crossref
[84]
Thulke D, Daheim N, Dugast C, Ney H. Efficient retrieval augmented generation from unstructured knowledge for task-oriented dialog. arXiv: 2102.04643, 2021. https://arxiv.org/abs/2102.04643, May 2024.
[85]
Nogueira R, Cho K. Passage re-ranking with BERT. arXiv: 1901.04085, 2019. https://arxiv.org/abs/1901.04085, May 2024.
[86]
Peng W J, Li G Y, Jiang Y, Wang Z L, Ou D, Zeng X Y, Xu T, Chen E H. Large language model based long-tail query rewriting in Taobao search. arXiv: 2311.03758, 2023. https://arxiv.org/abs/2311.03758, May 2024.
[87]
Gao L Y, Ma X G, Lin J, Callan J. Precise zero-shot dense retrieval without relevance labels. In Proc. the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1), Jul. 2023, pp.1762–1777. DOI: 10.18653/v1/2023.acl-long.99.
Crossref
[88]
Zhang W, Feng Y, Meng F D, You D, Liu Q. Bridging the gap between training and inference for neural machine translation. In Proc. the 57th Annual Meeting of the Association for Computational Linguistics, Jul. 2019, pp.4334–4343. DOI: 10.18653/v1/P19-1426.
Crossref
[89]
Gu J T, Lu Z D, Li H, Li V O K. Incorporating copying mechanism in sequence-to-sequence learning. In Proc. the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1), Aug. 2016, pp.1631–1640. DOI: 10.18653/v1/P16-1154.
Crossref
[90]
See A, Liu P J, Manning C D. Get to the point: Summarization with pointer-generator networks. In Proc. the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1), Jul. 2017, pp.1073–1083. DOI: 10.18653/v1/P17-1099.
Crossref
[91]
He S Z, Liu C, Liu K, Zhao J. Generating natural answers by incorporating copying and retrieving mechanisms in sequence-to-sequence learning. In Proc. the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1), Jul. 2017, pp.199–208. DOI: 10.18653/v1/P17-1019.
Crossref
[92]

Presti L L, Maggiore G, Marino V, Resciniti R. Mobile instant messaging apps as an opportunity for a conversational approach to marketing: A segmentation study. Journal of Business & Industrial Marketing, 2022, 37(7): 1432–1448. DOI: 10.1108/JBIM-02-2020-0121.
Crossref Google Scholar
[93]

McLean G, Osei-Frimpong K. Examining satisfaction with the experience during a live chat service encounter-implications for website providers. Computers in Human Behavior, 2017, 76: 494–508. DOI: 10.1016/j.chb.2017.08.005.
Crossref Google Scholar
[94]

Okonkwo C W, Ade-Ibijola A. Chatbots applications in education: A systematic review. Computers and Education: Artificial Intelligence, 2021, 2: 100033. DOI: 10.1016/ j.caeai.2021.100033.
Crossref Google Scholar
[95]

Pradana A, Sing G O, Kumar Y J. SamBot-intelligent conversational bot for interactive marketing with consumer-centric approach. International Journal of Computer Information Systems and Industrial Management Applications, 2014, 6: 265–275.
Google Scholar
[96]
Cui L, Huang S H, Wei F R, Tan C Q, Duan C Q, Zhou M. SuperAgent: A customer service chatbot for E-commerce websites. In Proc. the 55th Annual Meeting of the Association for Computational Linguistics-System Demonstrations, Jul. 2017, pp.97–102.
Crossref
[97]
Chen S Q, Li C L, Ji F, Zhou W, Chen H Q. Review-driven answer generation for product-related questions in E-commerce. In Proc. the 12th ACM International Conference on Web Search and Data Mining, Feb. 2019, pp.411–419. DOI: 10.1145/3289600.3290971.
Crossref
[98]
Xu Z T, Cruz M J, Guevara M et al. Retrieval-augmented generation with knowledge graphs for customer service question answering. arXiv: 2404.17723, 2024. https://arxiv.org/abs/2404.17723, May 2024.
[99]

Rutten L J F, Blake K D, Greenberg-Worisek A J, Allen S V, Moser R P, Hesse B W. Online health information seeking among us adults: Measuring progress toward a healthy people 2020 objective. Public Health Reports, 2019, 134(6): 617–625. DOI: 10.1177/0033354919874074.
Crossref Google Scholar
[100]

Baker A, Perov Y, Middleton K, Baxter J, Mullarkey D, Sangar D, Butt M, DoRosario A, Johri S. A comparison of artificial intelligence and human doctors for the purpose of triage and diagnosis. Frontiers in Artificial Intelligence, 2020, 3: 543405. DOI: 10.3389/frai.2020.543405.
Crossref Google Scholar
[101]
Cameron G, Cameron D, Megaw G, Bond R, Mulvenna M, O’Neill S, Armour C, McTear M. Assessing the usability of a chatbot for mental health care. In Proc. the 2018 International Workshops on Internet Science, Oct. 2018, pp.121–132. DOI: 10.1007/978-3-030-17705-8_11.
Crossref
[102]
Zakka C, Shad R, Chaurasia A et al. Almanac — Retrieval-augmented language models for clinical medicine. NEJM AI, 2024, 1(2): aioa2300068. DOI: 10.1056/aioa2300068.
Crossref
[103]
Jin M Y, Yu Q K, Shu D, Zhang C, Fan L Z, Hua W Y, Zhu S Y, Meng Y D, Wang Z T, Du M N, Zhang Y F. Health-LLM: Personalized retrieval-augmented disease prediction system. arXiv: 2402.00746, 2024. https://arxiv.org/abs/2402.00746, May 2024.
[104]
Gao Y J, Li R Z, Caskey J R, Dligach D, Miller T, Churpek M M, Afshar M. Leveraging a medical knowledge graph into large language models for diagnosis prediction. arXiv: 2308.14321, 2023. https://arxiv.org/abs/2308.14321, May 2024.
Crossref
[105]
Wu K, Wu E, Cassasola A et al. How well do LLMs cite relevant medical references? An evaluation framework and analyses. arXiv: 2402.02008, 2024. https://arxiv.org/abs/2402.02008, May 2024.
Crossref
[106]
Hobert S, von Wolff R M. Say hello to your new automated tutor—A structured literature review on pedagogical conversational agents. In Proc. the 14th Internationale Tagung Wirtschaftsinformatik, Feb. 2019, pp.301–314.
[107]

Wollny S, Schneider J, Di Mitri D, Weidlich J, Rittberger M, Drachsler H. Are we there yet?—A systematic literature review on chatbots in education. Frontiers in Artificial Intelligence, 2021, 4: 654924. DOI: 10.3389/frai.2021.654924.
Crossref Google Scholar
[108]
Settles B, Meeder B. A trainable spaced repetition model for language learning. In Proc. the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1), Aug. 2016, pp.1848–1858. DOI: 10.18653/v1/P16-1174.
Crossref
[109]
Long M H. The role of the linguistic environment in second language acquisition. In Handbook of Research on Language Acquisition: Vol. 2. Second Language Acquisition, Ritchie W C, Bhatia T K (eds.), Academic Press, 1996, pp.413–468.
Crossref
[110]
Chhibber N, Law E. Using conversational agents to support learning by teaching. arXiv: 1909.13443, 2019. https://arxiv.org/abs/1909.13443, May 2024.
[111]
McMahan A. Immersion, engagement, and presence: A method for analyzing 3-D video games. In The Video Game Theory Reader, Wolf M J P, Perron B (eds.), Routledge, 2013, pp.89–108.
[112]
Mateas M, Stern A. Natural language understanding in façade: Surface-text processing. In Proc. the 2nd International Conference on Technologies for Interactive Digital Storytelling and Entertainment, Jun. 2004, pp.3–13. DOI: 10.1007/978-3-540-27797-2_2.
Crossref
[113]
Rastogi A, Zang X X, Sunkara S, Gupta R, Khaitan P. Towards scalable multi-domain conversational agents: The schema-guided dialogue dataset. In Proc. the 34th AAAI Conference on Artificial Intelligence, Feb. 2020, pp.8689–8696. DOI: 10.1609/aaai.v34i05.6394.
Crossref
[114]
Dingliwal S, Gao B Y, Agarwal S, Lin C W, Chung T, Hakkani-Tür D Z. Few shot dialogue state tracking using meta-learning. In Proc. the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, Apr. 2021, pp.1730–1739. DOI: 10.18653/v1/2021.eacl-main.148.
Crossref
[115]
Chen Z Y, Liu B. Lifelong Machine Learning (2nd edition). Springer, 2018.
Crossref
[116]
Mazumder S, Ma N Z, Liu B. Towards a continuous knowledge learning engine for chatbots. arXiv: 1802.06024, 2018. https://arxiv.org/abs/1802.06024, May 2024.
[117]
Tuan Y L, Chen Y N, Lee H Y. DyKgChat: Benchmarking dialogue generation grounding on dynamic knowledge graphs. In Proc. the 2019 EMNLP-IJCNLP, Nov. 2019, pp.1855–1865. DOI: 10.18653/v1/D19-1194.
Crossref
[118]
Yurchenko O, Cherednichenko O, Trofimova-Herman A, Kupriianov Y. Towards cross-lingual transfer based on self-learning conversational agent model. In Proc. the 7th International Conference on Computational Linguistics and Intelligent Systems, Apr. 2023, pp.194–205.
[119]
Korbak T, Elsahar H, Kruszewski G, Dymetman M. Controlling conditional language models without catastrophic forgetting. In Proc. the 39th International Conference on Machine Learning, Jul. 2022, pp.11499–11528.
[120]

Gibson E, Futrell R, Piantadosi S P, Dautriche I, Mahowald K, Bergen L, Levy R. How efficiency shapes human language. Trends in Cognitive Sciences, 2019, 23(5): 389–407. DOI: 10.1016/j.tics.2019.02.003.
Crossref Google Scholar
[121]

Schrimpf M, Blank I A, Tuckute G et al. The neural architecture of language: Integrative modeling converges on predictive processing. Proceedings of the National Academy of Sciences of the United States of America, 2021, 118(45): e2105646118. DOI: 10.1073/pnas.2105646118.
Crossref Google Scholar
[122]

Feine J, Gnewuch U, Morana S, Maedche A. A taxonomy of social cues for conversational agents. International Journal of Human-Computer Studies, 2019, 132: 138–161. DOI: 10.1016/j.ijhcs.2019.07.009.
Crossref Google Scholar
[123]
Xu J, Wang H F, Niu Z Y, Wu H, Che W X, Liu T. Conversational graph grounded policy learning for open-domain conversation generation. In Proc. the 58th Annual Meeting of the Association for Computational Linguistics, Jul. 2020, pp.1835–1845. DOI: 10.18653/v1/2020.acl-main.166.
Crossref
[124]

Mirzababaei B, Pammer-Schindler V. Developing a conversational agent’s capability to identify structural wrongness in arguments based on Toulmin’s model of arguments. Frontiers in Artificial Intelligence, 2021, 4: 645516. DOI: 10.3389/FRAI.2021.645516.
Crossref Google Scholar
[125]
Nogueira D M, Maciel C, Viterbo J, Vecchiato D. A privacy-driven data management model for smart personal assistants. In Proc. the 5th Int. Conf. Human Aspects of Information Security, Privacy and Trust, Jul. 2017, pp.722–738. DOI: 10.1007/978-3-319-58460-7_49.
Crossref
[126]
Dubiel M, Halvey M, Azzopardi L. A survey investigating usage of virtual personal assistants. arXiv: 1807.04606, 2018. https://arxiv.org/abs/1807.04606, May 2024.
[127]

Motger Q, Franch X, Marco J. Software-based dialogue systems: Survey, taxonomy, and challenges. ACM Computing Surveys, 2022, 55(5): 91. DOI: 10.1145/3527450.
Crossref Google Scholar
[128]
Lai S T, Leu F Y, Lin J W. A banking chatbot security control procedure for protecting user data security and privacy. In Proc. the 13th Int. Conf. Broadband and Wireless Computing, Communication and Applications, Oct. 2018, pp.561–571. DOI: 10.1007/978-3-030-02613-4_50.
Crossref
[129]

Laranjo L, Dunn A G, Tong H L et al. Conversational agents in healthcare: A systematic review. Journal of the American Medical Informatics Association, 2018, 25(9): 1248–1258. DOI: 10.1093/jamia/ocy072.
Crossref Google Scholar
[130]
Escobar-Planas M. Towards trustworthy conversational agents for children. In Proc. the 21st Annual ACM Interaction Design and Children Conference, Jun. 2022, pp.693–695. DOI: 10.1145/3501712.3538826.
Crossref
[131]
Huang X W, Ruan W J, Huang W et al. A survey of safety and trustworthiness of large language models through the lens of verification and validation. arXiv: 2305.11391, 2023. https://arxiv.org/abs/2305.11391, May 2024.
Journal of Computer Science and Technology
Volume 39 Issue 3,
May 2024
Pages 585-609
DOI: 10.1007/s11390-024-2883-4
Cite this article:
Caffaro F, Rizzo G. Knowledge-Enhanced Conversational Agents. Journal of Computer Science and Technology, 2024, 39(3): 585-609. https://doi.org/10.1007/s11390-024-2883-4

202

Views

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 03 October 2022
Accepted: 27 April 2024
Published: 22 July 2024
© Institute of Computing Technology, Chinese Academy of Sciences 2024
Return