2000 character limit reached
Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement (2401.14215v3)
Published 25 Jan 2024 in cs.CL and cs.AI
Abstract: Memorizing and utilizing speakers' personas is a common practice for response generation in long-term conversations. Yet, human-authored datasets often provide uninformative persona sentences that hinder response quality. This paper presents a novel framework that leverages commonsense-based persona expansion to address such issues in long-term conversation. While prior work focuses on not producing personas that contradict others, we focus on transforming contradictory personas into sentences that contain rich speaker information, by refining them based on their contextual backgrounds with designed strategies. As the pioneer of persona expansion in multi-session settings, our framework facilitates better response generation via human-like persona refinement. The supplementary video of our work is available at https://caffeine-15bbf.web.app/.
- Towards a human-like open-domain chatbot. arXiv preprint arXiv:2001.09977.
- Keep me updated! memory management in long-term conversations. arXiv preprint arXiv:2210.08750.
- Swoosh: a generic approach to entity resolution. The VLDB Journal, 18:255–276.
- Dialogue chain-of-thought distillation for commonsense-aware conversational agents. The 2023 Conference on Empirical Methods in Natural Language Processing (forthcoming).
- Entity disambiguation for knowledge base population. In Proceedings of the 23rd International Conference on Computational Linguistics.
- ComFact: A benchmark for linking contextual commonsense knowledge. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1656–1675, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cicero: A dataset for contextualized commonsense inference in dialogues. arXiv preprint arXiv:2203.13926.
- (comet-) atomic 2020: on symbolic and neural commonsense knowledge graphs. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 6384–6392.
- Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118.
- Persona expansion with commonsense knowledge for diverse and consistent response generation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1131–1141.
- Dual task framework for improving persona-grounded dialogue dataset. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 10912–10920.
- Enhancing dialogue generation with conversational concept flows. In Findings of EACL.
- Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74–81.
- Lost in the middle: How language models use long contexts. arXiv preprint arXiv:2307.03172.
- Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
- Think beyond words: Exploring context-relevant visual commonsense for diverse dialogue generation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3106–3117, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Fabrizio Macagno and Sarah Bigi. 2018. Types of dialogue and pragmatic ambiguity. Argumentation and Language—Linguistic, Cognitive and Discursive Explorations, pages 191–218.
- Like hiking? you probably enjoy nature: Persona-grounded dialog with commonsense expansions. arXiv preprint arXiv:2010.03205.
- OpenAI. 2023. Chatgpt. https://openai.com/blog/chatgpt.
- Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730–27744.
- Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
- Context dependence of personalities: risk-taking behavior in a social and a nonsocial situation. Behavioral Ecology, 16(4):716–723.
- Dialogue natural language inference. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3731–3741, Florence, Italy. Association for Computational Linguistics.
- A broad-coverage challenge corpus for sentence understanding through inference. arXiv preprint arXiv:1704.05426.
- Section-aware commonsense knowledge-grounded dialogue generation with pre-trained language model. In Proceedings of the 29th International Conference on Computational Linguistics, pages 521–531, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
- Beyond goldfish memory: Long-term open-domain conversation. arXiv preprint arXiv:2107.07567.
- Personalizing dialogue agents: I have a dog, do you have pets too? arXiv preprint arXiv:1801.07243.
- Reflect, not reflex: Inference-based common ground improves dialogue response quality. arXiv preprint arXiv:2211.09267.
- Think before you speak: Explicitly generating implicit commonsense knowledge for response generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1237–1252, Dublin, Ireland. Association for Computational Linguistics.
- Hana Kim (7 papers)
- Kai Tzu-iunn Ong (10 papers)
- Seoyeon Kim (7 papers)
- Dongha Lee (63 papers)
- Jinyoung Yeo (46 papers)