Message Passing for Complex Question Answering over Knowledge Graphs. Vakulenko, S., Fernández, J., Polleres, A., de Rijke, M., & Cochez, M. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM2019, pages 1431–1440, Beijing, China, November, 2019. ACM.
Message Passing for Complex Question Answering over Knowledge Graphs [link]Paper  doi  abstract   bibtex   
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. Our approach outperforms the state-of-the-art on the LC-QuAD benchmark. Moreover, our error analysis reveals correct answers missing from the benchmark dataset and inconsistencies in the DBpedia knowledge graph.
@inproceedings{vaku-etal-2019CIKM,
  author = {Svitlana Vakulenko and Javier Fern{\'a}ndez and Axel Polleres and Maarten de Rijke and Michael Cochez},
  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. Our approach outperforms the state-of-the-art on the LC-QuAD benchmark. Moreover, our error analysis reveals correct answers missing from the benchmark dataset and inconsistencies in the DBpedia knowledge graph.},
  type = CONF,
  title = {Message Passing for Complex Question Answering over Knowledge Graphs},
  booktitle = {Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM2019},
day = {3--7},
pages = {1431--1440},
publisher = {ACM},
doi = {10.1145/3357384.3358026},
month = nov,
year = 2019,
Address = {Beijing, China},
url = {https://arxiv.org/abs/1908.06917},
}

Downloads: 0