SumRec: A Framework for Recommendation using Open-Domain Dialogue

• URL: http://arxiv.org/abs/2402.04523v1
• Date: Wed, 7 Feb 2024 02:06:48 GMT
• Title: SumRec: A Framework for Recommendation using Open-Domain Dialogue
• Authors: Ryutaro Asahara, Masaki Takahashi, Chiho Iwahashi, Michimasa Inaba
• Abstract summary: This study proposes a novel framework SumRec for recommending information from open-domain chat dialogue. The SumRec framework employs a large language model (LLM) to generate a summary of the speaker information from a dialogue. The speaker and item information are then input into a score estimation model, generating a recommendation score.
• Score: 4.552428235927528
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Chat dialogues contain considerable useful information about a speaker's interests, preferences, and experiences.Thus, knowledge from open-domain chat dialogue can be used to personalize various systems and offer recommendations for advanced information.This study proposed a novel framework SumRec for recommending information from open-domain chat dialogue.The study also examined the framework using ChatRec, a newly constructed dataset for training and evaluation. To extract the speaker and item characteristics, the SumRec framework employs a large language model (LLM) to generate a summary of the speaker information from a dialogue and to recommend information about an item according to the type of user.The speaker and item information are then input into a score estimation model, generating a recommendation score.Experimental results show that the SumRec framework provides better recommendations than the baseline method of using dialogues and item descriptions in their original form. Our dataset and code is publicly available at https://github.com/Ryutaro-A/SumRec

Related papers

• Refining Text Generation for Realistic Conversational Recommendation via Direct Preference Optimization [0.8594140167290097]
  Conversational Recommender Systems (CRSs) aim to elicit user preferences via natural dialogue to provide suitable item recommendations.<n>Current CRSs often deviate from realistic human interactions by rapidly recommending items in brief sessions.<n>This work addresses this gap by leveraging Large Language Models (LLMs) to generate dialogue summaries from dialogue history and item recommendation information.
  arXiv  Detail & Related papers  (2025-08-27T14:24:13Z)
• STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation [18.833994388759326]
  We introduce STEP, a conversational recommender centered on pre-trained language models.<n> STEP combines curriculum-guided context-knowledge fusion with lightweight task-specific prompt tuning.<n> Experimental results show that STEP outperforms mainstream methods in the precision of recommendation and dialogue quality in two public datasets.
  arXiv  Detail & Related papers  (2025-08-14T14:08:21Z)
• Beyond Whole Dialogue Modeling: Contextual Disentanglement for Conversational Recommendation [22.213312621287482]
  This paper proposes a novel model to introduce contextual disentanglement for improving conversational recommender systems. DisenCRS employs a dual disentanglement framework, including self-supervised contrastive disentanglement and counterfactual inference disentanglement. Experimental results on two widely used public datasets demonstrate that DisenCRS significantly outperforms existing conversational recommendation models.
  arXiv  Detail & Related papers  (2025-04-24T10:33:26Z)
• REGEN: A Dataset and Benchmarks with Natural Language Critiques and Narratives [4.558818396613368]
  We extend the Amazon Product Reviews dataset by inpainting two key natural language features. The narratives include product endorsements, purchase explanations, and summaries of user preferences.
  arXiv  Detail & Related papers  (2025-03-14T23:47:46Z)
• Snippet-based Conversational Recommender System [7.943863017830094]
  We introduce SnipRec, a novel CRS that enhances dialogues and recommendations by extracting diverse expressions and preferences from user-generated content (UGC) like customer reviews. Our approach eliminates the need for domain-specific training, making it adaptable to new domains and effective without prior knowledge of user preferences.
  arXiv  Detail & Related papers  (2024-11-09T04:23:58Z)
• Parameter-Efficient Conversational Recommender System as a Language Processing Task [52.47087212618396]
  Conversational recommender systems (CRS) aim to recommend relevant items to users by eliciting user preference through natural language conversation. Prior work often utilizes external knowledge graphs for items' semantic information, a language model for dialogue generation, and a recommendation module for ranking relevant items. In this paper, we represent items in natural language and formulate CRS as a natural language processing task.
  arXiv  Detail & Related papers  (2024-01-25T14:07:34Z)
• Conversational Recommendation as Retrieval: A Simple, Strong Baseline [4.737923227003888]
  Conversational recommendation systems (CRS) aim to recommend suitable items to users through natural language conversation. Most CRS approaches do not effectively utilize the signal provided by these conversations. We propose an alternative information retrieval (IR)-styled approach to the CRS item recommendation task.
  arXiv  Detail & Related papers  (2023-05-23T06:21:31Z)
• Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models [115.7508325840751]
  The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs) In this paper, we embark on an investigation into the utilization of ChatGPT for conversational recommendation, revealing the inadequacy of the existing evaluation protocol. We propose an interactive Evaluation approach based on LLMs named iEvaLM that harnesses LLM-based user simulators.
  arXiv  Detail & Related papers  (2023-05-22T15:12:43Z)
• Talk the Walk: Synthetic Data Generation for Conversational Music Recommendation [62.019437228000776]
  We present TalkWalk, which generates realistic high-quality conversational data by leveraging encoded expertise in widely available item collections. We generate over one million diverse conversations in a human-collected dataset.
  arXiv  Detail & Related papers  (2023-01-27T01:54:16Z)
• DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization [127.714919036388]
  DIONYSUS is a pre-trained encoder-decoder model for summarizing dialogues in any new domain. Our experiments show that DIONYSUS outperforms existing methods on six datasets.
  arXiv  Detail & Related papers  (2022-12-20T06:21:21Z)
• COLA: Improving Conversational Recommender Systems by Collaborative Augmentation [9.99763097964222]
  We propose a collaborative augmentation (COLA) method to improve both item representation learning and user preference modeling. We construct an interactive user-item graph from all conversations, which augments item representations with user-aware information. To improve user preference modeling, we retrieve similar conversations from the training corpus, where the involved items and attributes that reflect the user's potential interests are used to augment the user representation.
  arXiv  Detail & Related papers  (2022-12-15T12:37:28Z)
• COOKIE: A Dataset for Conversational Recommendation over Knowledge Graphs in E-commerce [64.95907840457471]
  We present a new dataset for conversational recommendation over knowledge graphs in e-commerce platforms called COOKIE. The dataset is constructed from an Amazon review corpus by integrating both user-agent dialogue and custom knowledge graphs for recommendation.
  arXiv  Detail & Related papers  (2020-08-21T00:11:31Z)
• Towards Conversational Recommendation over Multi-Type Dialogs [78.52354759386296]
  We propose a new task of conversational recommendation over multi-type dialogs, where the bots can proactively and naturally lead a conversation from a non-recommendation dialog to a recommendation dialog. To facilitate the study of this task, we create a human-to-human Chinese dialog dataset emphDuRecDial (about 10k dialogs, 156k utterances) In each dialog, the recommender proactively leads a multi-type dialog to approach recommendation targets and then makes multiple recommendations with rich interaction behavior.
  arXiv  Detail & Related papers  (2020-05-08T11:01:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.