Improving embedded knowledge graph multi-hop question answering by introducing relational chain reasoning

Jin, Weiqiang; Zhao, Biao; Yu, Hang; Tao, Xi; Yin, Ruiping; Liu, Guizhong

doi:10.1007/s10618-022-00891-8

Cited by 40 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our study, inspired by the outstanding results demonstrated in previous work, especially those of EmbedKGQA [31] and Rce-KGQA, proposed by Jin et al [32], we explore the use of knowledge graph (KG) embedding techniques to solve some problems that are difficult to cope with through traditional methods, such as the inference of implicit relations and the handling of subgraph localization. We found that by embedding the global relational knowledge and structural information of KG into a continuous low-dimensional space, we can not only simplify the processing flow of KG, but also expect to improve the overall accuracy of the question answering process.…”

Section: Kg Embedding Generatormentioning

confidence: 99%

Knowledge Graph Multi-Hop Question Answering Based on Dependent Syntactic Semantic Augmented Graph Networks

Cai,

Ma,

Hou

et al. 2024

Electronics

View full text Add to dashboard Cite

In the rapidly evolving domain of question answering systems, the ability to integrate machine comprehension with relational reasoning stands paramount. This paper introduces a novel architecture, the Dependent Syntactic Semantic Augmented Graph Network (DSSAGN), designed to address the intricate challenges of multi-hop question answering. By ingeniously leveraging the synergy between syntactic structures and semantic relationships within knowledge graphs, DSSAGN offers a breakthrough in interpretability, scalability, and accuracy. Unlike previous models that either fall short in handling complex relational paths or lack transparency in reasoning, our framework excels by embedding a sophisticated mechanism that meticulously models multi-hop relations and dynamically prioritizes the syntactic–semantic context.

show abstract

Section: Kg Embedding Generatormentioning

confidence: 99%

Knowledge Graph Multi-Hop Question Answering Based on Dependent Syntactic Semantic Augmented Graph Networks

Cai,

Ma,

Hou

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Jin et al [20] proposed a novel approach, namely relational chain-based embedded KGQA, which can simultaneously take advantage of the knowledge graph embedding and train with weak supervision by predicting the intermediate relational chain implied in KG to perform the multi-hop KGQA task. The module can address the incompleteness problem brought by the missing links in the incomplete knowledge graph thanks to its capability of capturing implicit KG relations.…”

Section: Related Workmentioning

confidence: 99%

Multi-Hop Knowledge Graph Question Answer Method Based on Relation Knowledge Enhancement

et al. 2023

View full text Add to dashboard Cite

Multi-hop knowledge graph question answer (KGQA) is a challenging task because it requires reasoning over multiple edges of the knowledge graph (KG) to arrive at the right answer. However, KGs are often incomplete with many missing links, posing additional challenges for multi-hop KGQA. Recent research on multi-hop KGQA attempted to deal with KG sparsity with relevant external texts. In our work, we propose a multi-hop KGQA model based on relation knowledge enhancement (RKE-KGQA), which fuses both label and text relations through global attention for relation knowledge augmentation. It is well known that the relation between entities can be represented by labels in the knowledge graph or texts in the text corpus, and multi-hop KGQA needs to jump across different entities through relations. First, we assign an activation probability to each entity, then calculate a score for the enhancement relation, and then transfer the score through the activated relations and, finally, obtain the answer. We carry out extensive experiments on three datasets and demonstrate that RKE-KGQA achieves the outperformance result.

show abstract

“…Recent studies have highlighted the need to use implicit messages to detect textual content (ElSherief et al, 2021 ). Knowledge graphs have been constructed to answer user questions by identifying the reasoning relations (Jin et al, 2023b ). Similarly, an external knowledge base was used with the transformer to perform emotion recognition and bias prediction (Ghosal et al, 2020 ; Swati and Grobelnik, 2022 ).…”

Section: Related Workmentioning

confidence: 99%

Profiling the barriers to the spreading of news using news headlines

Sittar,

Mladenić,

Grobelnik

2023

Front. Artif. Intell.

View full text Add to dashboard Cite

News headlines can be a good data source for detecting the barriers to the spreading of news in news media, which can be useful in many real-world applications. In this study, we utilize semantic knowledge through the inference-based model COMET and the sentiments of news headlines for barrier classification. We consider five barriers, including cultural, economic, political, linguistic, and geographical and different types of news headlines, including health, sports, science, recreation, games, homes, society, shopping, computers, and business. To that end, we collect and label the news headlines automatically for the barriers using the metadata of news publishers. Then, we utilize the extracted common-sense inferences and sentiments as features to detect the barriers to the spreading of news. We compare our approach to the classical text classification methods, deep learning, and transformer-based methods. The results show that (1) the inference-based semantic knowledge provides distinguishable inferences across the 10 categories that can increase the effectiveness and enhance the speed of the classification model; (2) the news of positive sentiments cross the political barrier, whereas the news of negative sentiments cross the cultural, economic, linguistic, and geographical barriers; (3) the proposed approach using inferences-based semantic knowledge and sentiment improves performance compared with using only headlines in barrier classification. The average F1-score for 4 out of 5 barriers has significantly improved as follows: for cultural barriers from 0.41 to 0.47, for economic barriers from 0.39 to 0.55, for political barriers from 0.59 to 0.70 and for geographical barriers from 0.59 to 0.76.

show abstract

Improving embedded knowledge graph multi-hop question answering by introducing relational chain reasoning

Cited by 40 publications

References 36 publications

Knowledge Graph Multi-Hop Question Answering Based on Dependent Syntactic Semantic Augmented Graph Networks

Knowledge Graph Multi-Hop Question Answering Based on Dependent Syntactic Semantic Augmented Graph Networks

Multi-Hop Knowledge Graph Question Answer Method Based on Relation Knowledge Enhancement

Profiling the barriers to the spreading of news using news headlines

Contact Info

Product

Resources

About