KG-CRuSE: Recurrent Walks over Knowledge Graph for Explainable Conversation Reasoning using Semantic Embeddings

Sarkar, Rajdeep; Arčan, Mihael; McCrae, John P.

doi:10.18653/v1/2022.nlp4convai-1.9

Cited by 2 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, some works [ 12 , 13 , 14 , 15 ] explicitly represent the reasoning process as path traversal on the knowledge graph. These methods further enhance the transparency and interpretability of conversational agents.…”

Section: Related Workmentioning

confidence: 99%

“…Although optimizing knowledge prediction in this way enables the selection of more suitable knowledge for generating informative responses, the method of acquiring knowledge in this manner has limited interpretability. Therefore, some works [ 12 , 13 , 14 , 15 ] employ knowledge graph path traversal to represent the knowledge reasoning process, enhancing the transparency and interpretability of dialogue systems. However, these methods still have some limitations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

KRP-DS: A Knowledge Graph-Based Dialogue System with Inference-Aided Prediction

He,

Xu,

Zhu

et al. 2023

Sensors

View full text Add to dashboard Cite

With the popularity of ChatGPT, there has been increasing attention towards dialogue systems. Researchers are dedicated to designing a knowledgeable model that can engage in conversations like humans. Traditional seq2seq dialogue models often suffer from limited performance and the issue of generating safe responses. In recent years, large-scale pretrained language models have demonstrated their powerful capabilities across various domains. Many studies have leveraged these pretrained models for dialogue tasks to address concerns such as safe response generation. Pretrained models can enhance responses by carrying certain knowledge information after being pre-trained on large-scale data. However, when specific knowledge is required in a particular domain, the model may still generate bland or inappropriate responses, and the interpretability of such models is poor. Therefore, in this paper, we propose the KRP-DS model. We design a knowledge module that incorporates a knowledge graph as external knowledge in the dialogue system. The module utilizes contextual information for path reasoning and guides knowledge prediction. Finally, the predicted knowledge is used to enhance response generation. Experimental results show that our proposed model can effectively improve the quality and diversity of responses while having better interpretability, and outperforms baseline models in both automatic and human evaluations.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

KRP-DS: A Knowledge Graph-Based Dialogue System with Inference-Aided Prediction

He,

Xu,

Zhu

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…We utilize a Graph Attention Network (GAT) (Brody et al, 2022) to score each node and then sample to obtain the target for state 1 It has been demonstrated that using fact triples can help dialogue systems generate high-quality responses better than separate entities and relations. (Dziri et al, 2021;Sarkar et al, 2022). transition:…”

Section: Gatementioning

confidence: 99%

Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue

Qin,

Zhang,

Liang

et al. 2023

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

View full text Add to dashboard Cite

Accurate knowledge selection is critical in knowledge-grounded dialogue systems. Towards a closer look at it, we offer a novel perspective to organize existing literature, i.e., knowledge selection coupled with, after, and before generation. We focus on the third underexplored category of study, which can not only select knowledge accurately in advance, but has the advantage to reduce the learning, adjustment, and interpretation burden of subsequent response generation models, especially LLMs. We propose GATE, a generator-agnostic knowledge selection method, to prepare knowledge for subsequent response generation models by selecting context-related knowledge among different knowledge structures and variable knowledge requirements. Experimental results demonstrate the superiority of GATE, and indicate that knowledge selection before generation is a lightweight yet effective way to facilitate LLMs (e.g., ChatGPT) to generate more informative responses.

show abstract

KG-CRuSE: Recurrent Walks over Knowledge Graph for Explainable Conversation Reasoning using Semantic Embeddings

Cited by 2 publications

References 16 publications

KRP-DS: A Knowledge Graph-Based Dialogue System with Inference-Aided Prediction

KRP-DS: A Knowledge Graph-Based Dialogue System with Inference-Aided Prediction

Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue

Contact Info

Product

Resources

About