Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation

Abstract

Personalized dialogue systems explore the problem of generating responses that are consistent with the user's personality, which has raised much attention in recent years. Existing personalized dialogue systems have tried to extract user profiles from dialogue history to guide personalized response generation. Since the dialogue history is usually long and noisy, most existing methods truncate the dialogue history to model the user's personality. Such methods can generate some personalized responses, but a large part of dialogue history is wasted, leading to sub-optimal performance of personalized response generation. In this work, we propose to refine the user dialogue history on a large scale, based on which we can handle more dialogue history and obtain more abundant and accurate persona information. Specifically, we design an MSP model which consists of three personal information refiners and a personalized response generator. With these multi-level refiners, we can sparsely extract the most valuable information (tokens) from the dialogue history and leverage other similar users' data to enhance personalization. Experimental results on two real-world datasets demonstrate the superiority of our model in generating more informative and personalized responses.

Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback

“…4 For example, a title keyword search for 'personali' or 'personaliz' returns 124 articles from the ACL Anthology and a further 10 from the arXiv Computation and Language (cs.CL) subclass. These systems cover a wide range of tasks including dialogue [127,157,36,39,41,109,133,146,149,206,238,244], recipe or diet generation [147,87,159], summarisation [215,240], machine translation [156,153,194,237], QA [137,193], search and information retrieval [4,40,59,70,245], sentiment analysis [80,155,226], domain classification [129,114,113], entity resolution [132], and aggression or abuse detection [107,108]; and are applied to a number of societal domains such as education [118,163,241], medicine [3,15,225,235] and news consumption…”

Keep Me Updated! Memory Management in Long-term Conversations

“…In particular, personalized dialogue system has typically been studied either via utilizing predefined, explicitly stated user profile (Zhang et al, 2018), or via directly extracting user profile from dialogue history (Xu et al, 2022a,b). While the latter approach is preferred in recent research works (Zhong et al, 2022), long-term management of the obtained information is yet to be studied.…”

“…Leveraging the advancement of pre-trained language models (Devlin et al, 2019;Raffel et al, 2020;Brown et al, 2020;Kim et al, 2021), recent studies attempt to use the unstructured form of text as memory, which is expected to be advantageous in terms of generalizability and interpretability. Ma et al (2021) and Xu et al (2022b) selectively stored dialogue history with relevant information, while Zhong et al (2022) employed refiners to extract fine-grained information from dialogue history. Xu et al (2022a) summarized the dialogue history to avoid overflow and redundancy.…”

MCP: Self-supervised Pre-training for Personalized Chatbots with Multi-level Contrastive Sampling

“…This group of methods aims at using descriptive information (such as persona sentences or attribute tables) to generate personalized responses, but such information is hard to collect, and it cannot keep track of user interest changes. (3) Learning with implicit user profiles (Ma et al, 2021b;Zhong et al, 2022). These methods extract personalized information automatically from a user's dialogue history to generate personalized responses.…”

“…This one-size-fits-all strategy cannot satisfy the varying needs of users and is lean to generate safe but meaningless responses, such as "I don't know" (Li et al, 2016a;Zhu et al, 2020). To solve this problem, some researchers have begun to endow chatbots with personality and develop personalized chatbots Ma et al, 2021b;Zhong et al, 2022). When equipped with personal information (either given by a predefined profile or learning from dialogue history), personalized chatbots can generate more user-specific and informative responses.…”