Personalizing Dialogue Agents via Meta-Learning

By Zhaojiang Lin, Andrea Madotto, Chien-Sheng Wu, Pascale Fung. 2019

202 citations recorded by the source corpus.

Existing personalized dialogue models use human designed persona descriptions to improve dialogue consistency. Collecting such descriptions from existing dialogues is expensive and requires hand-crafted feature designs. In this paper, we propose to extend Model-Agnostic Meta-Learning (MAML) (Finn et al., 2017) to personalized dialogue learning without using any persona descriptions. Our model learns to quickly adapt to new personas by leveraging only a few dialogue samples collected from the same user, which is fundamentally different from conditioning the response on the persona descriptions. Empirical results on Persona-chat dataset (Zhang et al., 2018) indicate that our solution outperforms non-meta-learning baselines using automatic evaluation metrics, and in terms of human-evaluated fluency and consistency.

Subfields: Artificial Intelligence, Natural Language Processing, Reinforcement Learning, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Reinforcement Learning

In Human-Computer Interaction

Citations in the corpus

Survey of Hallucination in Natural Language Generation (2022, background): “While some works set their objective to teach models to utilize speaker-level embeddings [99, 112], the others condition generation with a set of descriptions about a persona, which we will discuss in detail in the next section.”
Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning (2020, methodology): “We use perplexity, BLEU, and Consistency score (Madotto et al., 2019) as evaluation metrics.”
Exploring Auxiliary Reasoning Tasks for Task-oriented Dialog Systems with Meta Cooperative Learning (2021, background): “Madotto et al. (2019) learned different personas as different tasks via meta-learning algorithms for personalized dialog systems.”
Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems (2020, background): “, 2019), pipelined endto-end models (Qian and Yu, 2019) and personalized dialogue systems (Madotto et al., 2019).”
PERSONACHATGEN: Generating Personalized Dialogues using GPT-3 (2022, methodology): “Madotto et al. (2019) used meta-learning to personalize dialogue agents.”
You Impress Me: Dialogue Generation via Mutual Persona Perception (2020, unknown): “Madotto et al. (2019) applied meta-learning to quickly adapt to new speakers, and Tigunova et al. (2019) extracted user attributes from daily dialogues.”
Tool Learning with Foundation Models (2023, unknown): “Existing works cover a wide range of tasks, such as dialogue generation (Madotto et al., 2019; Mazaré et al., 2018; Song et al., 2021; Zhong et al., 2022), machine translation (Mirkin & Meunier, 2015; Michel & Neubig, 2018; Wuebker et al.”
Improving Factual Consistency Between a Response and Persona Facts (2021, background): “The ﬁrst category includes systems that learn speaker-level embeddings from responses produced by a particular speaker (Li et al., 2016a; Madotto et al., 2019).”
Plug-and-Play Conversational Models (2020, background): “…involves overcoming a variety of challenges such as personalization (Li et al., 2016b; Zhang et al., 2018; Dinan et al., 2019; Wolf et al., 2019b; Madotto et al., 2019), knowledge grounding (Dinan et al., 2018; Gopalakrish-nan et al., 2019; Ghazvininejad et al., 2018; Moghe et al., 2018; Wu et…”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, methodology): “Madotto et al. (2019) proposed to use Model-Agnostic Meta-Learning (MAML) to adapt to new personas with only a few training samples and needed no persona description. Majumder et al. (2020a) relied on external knowledge sources to expand current persona descriptions so that richer persona descriptio”