CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge Graphs

Zhou, Jinfeng; Wang, Bo; He, Ran; Hou, Yuexian

doi:10.18653/v1/2021.emnlp-main.355

Cited by 23 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• CRFR (Zhou et al, 2021a): It performs flexible fragment reasoning on KGs to address their inherent incompleteness.…”

Section: Methodsmentioning

confidence: 99%

Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models

Wang,

Tang,

Zhao

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs), which rely on natural language conversations to satisfy user needs. In this paper, we embark on an investigation into the utilization of ChatGPT for CRSs, revealing the inadequacy of the existing evaluation protocol. It might overemphasize the matching with ground-truth items annotated by humans while neglecting the interactive nature of CRSs.To overcome the limitation, we further propose an interactive Evaluation approach based on LLMs, named iEvaLM, which harnesses LLM-based user simulators. Our evaluation approach can simulate various system-user interaction scenarios. Through the experiments on two public CRS datasets, we demonstrate notable improvements compared to the prevailing evaluation protocol. Furthermore, we emphasize the evaluation of explainability, and Chat-GPT showcases persuasive explanation generation for its recommendations. Our study contributes to a deeper comprehension of the untapped potential of LLMs for CRSs and provides a more flexible and realistic evaluation approach for future research about LLMbased CRSs. The code is available at https: //github.com/RUCAIBox/iEvaLM-CRS.

show abstract

“…• CRFR (Zhou et al, 2021a): It performs flexible fragment reasoning on KGs to address their inherent incompleteness.…”

Section: Methodsmentioning

confidence: 99%

Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models

Wang,

Tang,

Zhao

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…This approach considers multiple levels of contextual information to achieve highly accurate results. Zhou et al [17] proposed a knowledge graph-based dialogue recommendation model that leverages knowledge graphs and an attribute-based graph attention mechanism to combine multiple information sources. The model outperforms existing conversation models by obtaining better results.…”

Section: Related Work 21 Textual Dialogue Response Generationmentioning

confidence: 99%

Multimodal Dialogue Response Generation Based on Selective Attention and Gating Mechanisms

Yu,

Zhang,

Ding

et al. 2023

Preprint

View full text Add to dashboard Cite

Picture response is a crucial aspect in dialogue systems; however, existing systems predominantly focus on text information, often neglecting the use of image data or relying on large-scale language models, which leads to high training costs and slower generation speeds. To address these challenges, this paper introduces the MDSAGM (Selective Attention and Gating Mechanism)model, which comprises a Transformer-based Text Dialogue Response Generator, Text-to-Image Generation, and SAGM (Selective Attention and Gating Mechanism). The model is core lies in combining Selective Attention and Gating Mechanism to enhance generalization and improve model accuracy. The study further explores the contributions of image and text information in multimodal fusion. Compared to other large-scale training models, the proposed model demonstrates computational efficiency , fewer parameters, and shorter response times, making it more lightweight. This dialogue model facilitates the separation of multimodal dialogue parameters from the overall model, enabling better parameter fitting through pre-training with abundant plain text and text-image data. Extensive experiments show that the proposed method achieves promising results in both automatic and manual evaluations, generating information-rich text and image responses with higher accuracy while maintaining a lightweight structure.

show abstract

“…Similarly, early critiquing-based systems provide a systematic approach to elicit user's feedback on the recommended items' features and update the recommendations accordingly, see also [28,29]. Technological advancements particularly in fields like NLP, speech recognition, machine learning in general led to the design of today's end-to-end learning-based CRS, where recorded recommendation dialogs collected between paired-humans are used to train the deep neural models, see, e.g., [7,8,9,11]. Given the last user utterance or ongoing dialog history, these trained models are then used to compute and provide item recommendations and generate responses in natural language.…”

Section: Datasets and Data Qualitymentioning

confidence: 99%

“…play a pivotal role in supporting dialog systems design and implementation as these entities can be useful in finding explicit relationships with graphs representing domain knowledge [4,5]. Such explicit relations further seem to be helpful in modeling the users' preferences, see e.g., [6,7,8]. The elicited preferences and domain knowledge are then leveraged by the recommender algorithm in order to compute and provide items of interest to the users.…”

Section: Introductionmentioning

confidence: 99%

INSPIRED2: An Improved Dataset for Sociable Conversational Recommendation

Manzoor¹,

Jannach²

2022

Preprint

View full text Add to dashboard Cite

Conversational recommender systems (CRS) that interact with users in natural language utilize recommendation dialogs collected with the help of paired humans, where one plays the role of a seeker and the other as a recommender. These recommendation dialogs include items and entities to disclose seekers' preferences in natural language. However, in order to precisely model the seekers' preferences and respond consistently, mainly CRS rely on explicitly annotated items and entities that appear in the dialog, and usually leverage the domain knowledge. In this work, we investigate INSPIRED, a dataset consisting of recommendation dialogs for the sociable conversational recommendation, where items and entities were explicitly annotated using automatic keyword or pattern matching techniques. To this end, we found a large number of cases where items and entities were either wrongly annotated or missing annotations at all. The question however remains to what extent automatic techniques for annotations are effective. Moreover, it is unclear what is the relative impact of poor and improved annotations on the overall effectiveness of a CRS in terms of the consistency and quality of responses. In this regard, first, we manually fixed the annotations and removed the noise in the INSPIRED dataset. Second, we evaluate the performance of several benchmark CRS using both versions of the dataset. Our analyses suggest that with the improved version of the dataset, i.e., INSPIRED2, various benchmark CRS outperformed and that dialogs are rich in knowledge concepts compared to when the original version is used. We release our improved dataset (INSPIRED2) publicly at https://github.com/ahtsham58/INSPIRED2.

show abstract

CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge Graphs

Cited by 23 publications

References 28 publications

Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models

Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models

Multimodal Dialogue Response Generation Based on Selective Attention and Gating Mechanisms

INSPIRED2: An Improved Dataset for Sociable Conversational Recommendation

Contact Info

Product

Resources

About