Hao Wang
Bin Guo
Skip Abstract Section
Abstract
Knowledge-enhanced dialogue systems aim at generating factually correct and coherent responses by reasoning over knowledge sources, which is a promising research trend. The truly harmonious human-agent dialogue systems need to conduct engaging conversations from three aspects as humans, namely (1) stating factual contents (e.g., records in Wikipedia), (2) conveying subjective and informative opinions about objects (e.g., user discussions on Twitter), and (3) impressing interlocutors with diverse expression styles (e.g., personalized expression habits). The existing knowledge base is a standardized and unified coding for factual knowledge, which could not portray the other two kinds of knowledge to make responses more informative and expressive diverse. To address this, we present CrowdDialog, a crowd intelligence knowledge-enhanced dialogue system, which takes advantage of “crowd intelligence knowledge” extracted from social media (with rich subjective descriptions and diversified expression styles) to promote the performance of dialogue systems. Firstly, to thoroughly mine and organize the crowd intelligence knowledge underlying large-scale and unstructured online contents, we elaborately design the Crowd Intelligence Knowledge Graph (CIKG) structure, including the domain commonsense subgraph, descriptive subgraph, and expressive subgraph. Secondly, to reasonably integrate heterogeneous crowd intelligence knowledge into responses while ensuring logicality and fluency, we propose the Gated Fusion with Dynamic Knowledge-Dependent (GFDD) model, which generates responses from the semantic and syntactic perspective with the context-aware knowledge gate and dynamic knowledge decoding. Finally, extensive experiments over both Chinese and English dialogue datasets demonstrate that our approach GFDD outperforms competitive baselines in terms of both automatic evaluation and human judgments. Besides, ablation studies indicate that the proposed CIKG has the potential to promote dialogue systems to generate fluent, informative, and diverse dialogue responses.
- [1] . 2019. Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond. Transactions of the Association for Computational Linguistics 7, 1 (2019), 597–610.Google Scholar
Cross Ref
- [2] . 2021. Learning to copy coherent knowledge for response generation. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 12535–12543.Google ScholarCross Ref
- [3] . 2014. Easy access to the freebase dataset. In Proceedings of the 23rd International Conference on World Wide Web. 95–98.Google ScholarDigital Library
- [4] . 2008. Finding the right facts in the crowd: Factoid question answering over social media. In Proceedings of the 17th International Conference on World Wide Web. 467–476.Google ScholarDigital Library
- [5] . 2003. Latent dirichlet allocation. Journal of Machine Learning Research 3, Jan (2003), 993–1022.Google ScholarDigital Library
- [6] . 2008. Freebase: A collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data. 1247–1250.Google ScholarDigital Library
- [7] . 2013. Translating embeddings for modeling multi-relational data. Advances in Neural Information Processing Systems 26, 1 (2013), 2787–2795.Google Scholar
- [8] . 2009. Discriminative reordering with Chinese grammatical relations features. In Proceedings of the 3rd Workshop on Syntax and Structure in Statistical Translation (SSST-3) at NAACL HLT 2009. 51–59.Google ScholarCross Ref
- [9] . 2020. Bridging the gap between prior and posterior knowledge selection for knowledge-grounded dialogue generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 3426–3437.Google ScholarCross Ref
- [10] . 2014. Learning phrase representations using RNN encoder–decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 1724–1734.Google ScholarCross Ref
- [11] . 2019. ELECTRA: Pre-training text encoders as discriminators rather than generators. In Proceedings of the International Conference on Learning Representations.Google Scholar
- [12] . 2018. Wizard of Wikipedia: Knowledge-powered conversational agents. In Proceedings of the International Conference on Learning Representations.Google Scholar
- [13] . 2016. Deep biaffine attention for neural dependency parsing. arXiv:1611.01734. Retrieved from https://arxiv.org/abs/1611.01734.Google Scholar
- [14] . 2008. Towards human-like spoken dialogue systems. Speech Communication 50, 8-9 (2008), 630–645.Google ScholarDigital Library
- [15] . 2003. A survey of socially interactive robots. Robotics and Autonomous Systems 42, 3-4 (2003), 143–166.Google ScholarCross Ref
- [16] . 2011. CrowdDB: Answering queries with crowdsourcing. In Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data. 61–72.Google ScholarDigital Library
- [17] . 2020. From crowdsourcing to crowdmining: Using implicit human intelligence for better understanding of crowdsourced data. World Wide Web 23, 2 (2020), 1101–1125.Google ScholarCross Ref
- [18] . 2021. Conditional text generation for harmonious human-machine interaction. ACM Transactions on Intelligent Systems and Technology (TIST) 12, 2 (2021), 1–50.Google ScholarDigital Library
- [19] . 2015. Mobile crowd sensing and computing: The review of an emerging human-powered sensing paradigm. ACM Computing Surveys (CSUR) 48, 1 (2015), 1–31.Google ScholarDigital Library
- [20] . 2020. A framework to analyze the emotional reactions to mass violent events on Twitter and influential factors. Information Processing & Management 57, 6 (2020), 102372.Google ScholarCross Ref
- [21] . 2003. Topic-sensitive pagerank: A context-sensitive ranking algorithm for web search. IEEE Transactions on Knowledge and Data Engineering 15, 4 (2003), 784–796.Google ScholarDigital Library
- [22] . 2019. Knowledge graph embedding based question answering. In Proceedings of the 12th ACM International Conference on Web Search and Data Mining. 105–113.Google ScholarDigital Library
- [23] . 2020. Attnio: Knowledge graph exploration with in-and-out attention flow for knowledge-grounded dialogue. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 3484–3497.Google ScholarCross Ref
- [24] . 2020. Biased TextRank: Unsupervised graph-based content extraction. In Proceedings of the 28th International Conference on Computational Linguistics. 1642–1652.Google ScholarCross Ref
- [25] . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the NAACL-HLT. 4171–4186.Google Scholar
- [26] . 2014. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations. Retrieved from https://arxiv.org/abs/1412.6980.Google Scholar
- [27] . 2016. A persona-based neural conversation model. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 994–1003.Google ScholarCross Ref
- [28] . 2016. Deep reinforcement learning for dialogue generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 1192–1202.Google ScholarCross Ref
- [29] . 2021. Social media crowdsourcing for rapid damage assessment following a sudden-onset natural hazard event. International Journal of Information Management 601 (2021), 102378.Google ScholarDigital Library
- [30] . 2016. Dataset and neural recurrent sequence labeling model for open-domain factoid question answering. arXiv:1607.06275. Retrieved from https://arxiv.org/abs/1607.06275.Google Scholar
- [31] . 2017. Crowd intelligence in AI 2.0 era. Frontiers of Information Technology & Electronic Engineering 18, 1 (2017), 15–43.Google ScholarCross Ref
- [32] . 2019. Incremental transformer with deliberation decoder for document grounded conversations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 12–21.Google ScholarCross Ref
- [33] . 2020. Generating informative conversational response using recurrent knowledge-interaction and knowledge-copy. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 41–52.Google ScholarCross Ref
- [34] . 2020. Towards conversational recommendation over multi-type dialogs. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 1036–1049.Google ScholarCross Ref
- [35] . 2020. A survey on empathetic dialogue systems. Information Fusion 64, 1 (2020), 50–70.Google ScholarCross Ref
- [36] . 2020. Dukenet: A dual knowledge interaction network for knowledge-grounded conversation. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1151–1160.Google ScholarDigital Library
- [37] . 2004. Textrank: Bringing order into text. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing. 404–411.Google Scholar
- [38] . 2013. Efficient estimation of word representations in vector space. In Proceedings of the International Conference on Learning Representations. Retrieved from https://arxiv.org/abs/1301.3781.Google Scholar
- [39] . 2019. Opendialkg: Explainable conversational reasoning with attention-based walks over knowledge graphs. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 845–854.Google ScholarCross Ref
- [40] . 2015. Topic2Vec: Learning distributed representations of topics. In Proceedings of the 2015 International Conference on Asian Language Processing (IALP). IEEE, 193–196.Google Scholar
- [41] . 2020. Mtss: Learn from multiple domain teachers and become a multi-domain dialogue expert. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 8608–8615.Google ScholarCross Ref
- [42] . 2018. Improving language understanding by generative pre-training. (2018). https://www.bibsonomy.org/bibtex/273ced32c0d4588eb95b6986dc2c8147c/jonaskaiser.Google Scholar
- [43] . 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9.Google Scholar
- [44] . 2021. Recipes for building an open-domain chatbot. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 300–325.Google ScholarCross Ref
- [45] . 2017. Get to the point: Summarization with pointer-generator networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1073–1083.Google ScholarCross Ref
- [46] . 2016. Building end-to-end dialogue systems using generative hierarchical neural network models. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 30.Google ScholarCross Ref
- [47] . 2020. Cybersecurity event detection with new and re-emerging words. In Proceedings of the 15th ACM Asia Conference on Computer and Communications Security. 665–678.Google ScholarDigital Library
- [48] . 2017. Conceptnet 5.5: An open multilingual graph of general knowledge. In Proceedings of the 31st AAAI Conference on Artificial Intelligence.Google ScholarCross Ref
- [49] . 2015. End-to-end memory networks. Advances in Neural Information Processing Systems 2015, 1 (2015), 2440–2448.Google Scholar
- [50] . 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems. 5998–6008.Google Scholar
- [51] . 2018. Graph attention networks. In Proceedings of the International Conference on Learning Representations.Google Scholar
- [52] . 2015. A neural conversational model. arXiv:1506.05869. Retrieved from https://arxiv.org/abs/1506.05869.Google Scholar
- [53] . 2021. Towards information-rich, logical dialogue systems with knowledge-enhanced neural models. Neurocomputing 465, 1 (2021), 248–264.Google ScholarDigital Library
- [54] . 2018. Ripplenet: Propagating user preferences on the knowledge graph for recommender systems. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 417–426.Google ScholarDigital Library
- [55] . 2020. Improving knowledge-aware dialogue generation via knowledge base question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 9169–9176.Google ScholarCross Ref
- [56] . 2020. A large-scale chinese short-text conversation dataset. In Proceedings of the CCF International Conference on Natural Language Processing and Chinese Computing. Springer, 91–103.Google ScholarDigital Library
- [57] . 2021. More is better: Enhancing open-domain dialogue generation via multi-source heterogeneous knowledge. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2286–2300.Google ScholarCross Ref
- [58] . 2020. Diverse and informative dialogue generation with context-specific commonsense knowledge awareness. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 5811–5820.Google ScholarCross Ref
- [59] . 2021. Topicka: Generating commonsense knowledge-aware dialogue responses towards the recommended topic fact. In Proceedings of the 29th International Conference on International Joint Conferences on Artificial Intelligence. 3766–3772.Google Scholar
- [60] . 2019. Proactive human-machine conversation with explicit conversation goal. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 3794–3804.Google ScholarCross Ref
- [61] . 2021. Finding of urban rainstorm and waterlogging disasters based on microblogging data and the location-routing problem model of urban emergency logistics. In Proceedings of the Economic Impacts and Emergency Management of Disasters in China. Springer, 221–258.Google ScholarCross Ref
- [62] . 2000. The part-of-speech tagging guidelines for the Penn Chinese Treebank (3.0). IRCS Technical Reports Series (2000), 38.Google Scholar
- [63] . 2017. Explicit semantic ranking for academic search via knowledge graph embedding. In Proceedings of the 26th International Conference on World Wide Web. 1271–1279.Google ScholarDigital Library
- [64] . 2022. A survey of knowledge-enhanced text generation. ACM Computing Surveys (CSUR) 54, 11s (2022), 1–38.Google ScholarDigital Library
- [65] . 2020. Grounded conversation generation as guided traverses in commonsense knowledge graphs. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2031–2043.Google ScholarCross Ref
- [66] . 2020. DIALOGPT: Large-scale generative pre-training for conversational response generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. 270–278.Google ScholarCross Ref
- [67] . 2006. Humanoid social robots as a medium of communication. New Media & Society 8, 3 (2006), 401–419.Google ScholarCross Ref
- [68] . 2020. Knowledge-grounded dialogue generation with pre-trained language models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 3377–3390.Google ScholarCross Ref
- [69] . 2021. Knowledge-aware dialogue generation with hybrid attention (student abstract). In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 15951–15952.Google ScholarCross Ref
- [70] . 2021. EARL: Informative knowledge-grounded conversation generation with entity-agnostic representation learning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2383–2395.Google ScholarCross Ref
- [71] . 2018. Commonsense knowledge aware conversation generation with graph attention. In Proceedings of the 27th International Joint Conference on Artificial Intelligence. 4623–4629.Google ScholarDigital Library
- [72] . 2020. KdConv: A Chinese multi-domain dialogue dataset towards multi-turn knowledge-driven conversation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 7098–7108.Google ScholarCross Ref
- [73] . 2018. A dataset for document grounded conversations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 708–713.Google ScholarCross Ref
Index Terms
- Towards Informative and Diverse Dialogue Systems Over Hierarchical Crowd Intelligence Knowledge Graph
Recommendations
Towards Conversationally Intelligent Dialog Systems
CHI EA '22: Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing SystemsSpoken dialog systems, lacking the means to address the complex phenomena of spontaneous speech and conversational dynamics, force users into a constrained mode of dialog that resembles text-based interaction more closely than spoken conversation. Turn-...
Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers
The Semantic WebAbstractGenerating knowledge grounded responses in both goal and non-goal oriented dialogue systems is an important research challenge. Knowledge Graphs (KG) can be viewed as an abstraction of the real world, which can potentially facilitate a dialogue ...
Knowledge-graph based Proactive Dialogue Generation with Improved Meta-learning
IPMV '20: Proceedings of the 2020 2nd International Conference on Image Processing and Machine VisionKnowledge graph-based dialogue systems can narrow down knowledge candidates for generating informative and diverse responses with the use of prior information, e.g., triple attributes or graph paths. However, most current knowledge graphs (KG) cover ...
Comments