Leveraging Historical Interaction Data for Improving Conversational
Recommender System
- URL: http://arxiv.org/abs/2008.08247v1
- Date: Wed, 19 Aug 2020 03:43:50 GMT
- Title: Leveraging Historical Interaction Data for Improving Conversational
Recommender System
- Authors: Kun Zhou, Wayne Xin Zhao, Hui Wang, Sirui Wang, Fuzheng Zhang,
Zhongyuan Wang and Ji-Rong Wen
- Abstract summary: We propose a novel pre-training approach to integrate item- and attribute-based preference sequence.
Experiment results on two real-world datasets have demonstrated the effectiveness of our approach.
- Score: 105.90963882850265
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, conversational recommender system (CRS) has become an emerging and
practical research topic. Most of the existing CRS methods focus on learning
effective preference representations for users from conversation data alone.
While, we take a new perspective to leverage historical interaction data for
improving CRS. For this purpose, we propose a novel pre-training approach to
integrating both item-based preference sequence (from historical interaction
data) and attribute-based preference sequence (from conversation data) via
pre-training methods. We carefully design two pre-training tasks to enhance
information fusion between item- and attribute-based preference. To improve the
learning performance, we further develop an effective negative sample generator
which can produce high-quality negative samples. Experiment results on two
real-world datasets have demonstrated the effectiveness of our approach for
improving CRS.
Related papers
- Collaborative Retrieval for Large Language Model-based Conversational Recommender Systems [65.75265303064654]
Conversational recommender systems (CRS) aim to provide personalized recommendations via interactive dialogues with users.
Large language models (LLMs) enhance CRS with their superior understanding of context-aware user preferences.
We propose CRAG, Collaborative Retrieval Augmented Generation for LLM-based CRS.
arXiv Detail & Related papers (2025-02-19T22:47:40Z) - A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts.
With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS)
Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements.
High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
arXiv Detail & Related papers (2024-12-18T15:38:39Z) - Leveraging Knowledge Graph Embedding for Effective Conversational Recommendation [4.079573593766921]
We propose a knowledge graph based conversational recommender system (referred as KG-CRS)
Specifically, we first integrate the user-item graph and item-attribute graph into a dynamic graph, dynamically changing during the dialogue process by removing negative items or attributes.
We then learn informative embedding of users, items, and attributes by also considering propagation through neighbors on the graph.
arXiv Detail & Related papers (2024-08-02T15:38:55Z) - Improving Conversational Recommendation Systems via Bias Analysis and
Language-Model-Enhanced Data Augmentation [28.349599213528627]
Conversational Recommendation System (CRS) is a rapidly growing research area that has gained significant attention alongside advancements in language modelling techniques.
In this study, we delve into benchmark datasets for developing CRS models and address potential biases arising from the feedback loop inherent in multi-turn interactions.
We present two novel strategies, 'Once-Aug' and 'PopNudge', to enhance model performance while mitigating biases.
arXiv Detail & Related papers (2023-10-25T16:11:55Z) - Alleviating the Long-Tail Problem in Conversational Recommender Systems [72.8984755843184]
Conversational recommender systems (CRS) aim to provide the recommendation service via natural language conversations.
Existing CRS datasets suffer from the long-tail issue, ie a large proportion of items are rarely (or even never) mentioned in the conversations.
This paper presents textbfLOT-CRS, a novel framework that focuses on simulating and utilizing a balanced CRS dataset.
arXiv Detail & Related papers (2023-07-21T15:28:47Z) - Improving Conversational Recommendation Systems via Counterfactual Data
Simulation [73.4526400381668]
Conversational recommender systems (CRSs) aim to provide recommendation services via natural language conversations.
Existing CRS approaches often suffer from the issue of insufficient training due to the scarcity of training data.
We propose a CounterFactual data simulation approach for CRS, named CFCRS, to alleviate the issue of data scarcity in CRSs.
arXiv Detail & Related papers (2023-06-05T12:48:56Z) - 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) - C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational
Recommender System [47.18484863699936]
We propose a novel contrastive learning framework to improve data semantic fusion for Conversational recommender systems.
In our approach, we first extract and represent multi-grained semantic units from different data signals, and then align the associated multi-type semantic units in a coarse-to-fine way.
Experiments on two public CRS datasets have demonstrated the effectiveness of our approach in both recommendation and conversation tasks.
arXiv Detail & Related papers (2022-01-04T11:39:41Z)
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.