Proceedings of the 28th ACM International Conference on Information and Knowledge Management 2019
DOI: 10.1145/3357384.3358026
|View full text |Cite
|
Sign up to set email alerts
|

Message Passing for Complex Question Answering over Knowledge Graphs

Abstract: Question answering over knowledge graphs (KGQA) has evolved from simple single-fact questions to complex questions that require graph traversal and aggregation. We propose a novel approach for complex KGQA that uses unsupervised message passing, which propagates confidence scores obtained by parsing an input question and matching terms in the knowledge graph to a set of possible answers. First, we identify entity, relationship, and class names mentioned in a natural language question, and map these to their co… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
73
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
3

Relationship

1
7

Authors

Journals

citations
Cited by 60 publications
(73 citation statements)
references
References 40 publications
(84 reference statements)
0
73
0
Order By: Relevance
“…Our model outperforms QAmp [15] and WQAqua [3] 5 . We did not compare our model with [8], because their work does not consider entity detection and linking steps.…”
Section: Results Of the Kbqa System On Lc-quad10 Datasetmentioning
confidence: 94%
See 2 more Smart Citations
“…Our model outperforms QAmp [15] and WQAqua [3] 5 . We did not compare our model with [8], because their work does not consider entity detection and linking steps.…”
Section: Results Of the Kbqa System On Lc-quad10 Datasetmentioning
confidence: 94%
“…The model of [15] uses message passing for query ranking, which means propagation of confidence scores from candidate entities and relations to the adjacent nodes in the extracted subgraph. The model also includes entity and relation extraction steps.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…Knowledge graphs provide a structured way to represent information in the form of entities and relations between them [12]. They have become central to a variety of tasks in the Web, including information retrieval [6,13], question answering [19,43], and information extraction [4,14,26]. Many of these tasks can benefit from distributed representations of entities and relations, also known as embeddings.…”
Section: Introductionmentioning
confidence: 99%
“…Relation extraction is a classification task to find a relation among entities in unstructured texts. It can be applied to many natural language processing tasks, which require structured information, such as knowledge base construction [4,9,23,34], question answering [3,7,38,43], and recommender systems [2,6,16,42].…”
Section: Introductionmentioning
confidence: 99%