ABSTRACT
Over recent years, large knowledge bases have been constructed to store massive knowledge graphs. However, these knowledge graphs are highly incomplete. To solve this problem, we propose a web-based question answering system with multimodal fusion of unstructured and structured information, to fill in missing information for knowledge bases. To utilize unstructured information from the Web for knowledge graph construction, we design multimodal features and question templates to extract missing facts, which can achieve good quality with very few questions. The question answering system also employs structured information from knowledge bases, such as entity types and entity-to-entity relatedness, to help improve extraction quality. To improve system efficiency, we utilize a few query-driven techniques for web-based question answering to reduce the runtime and provide fast responses to user queries. Extensive experiments have been conducted to demonstrate the effectiveness and efficiency of our system.
- Pradeep K Atrey, M Anwar Hossain, Abdulmotaleb El Saddik, and Mohan S Kankanhalli. 2010. Multimodal fusion for multimedia analysis: a survey. Multimedia systems 16, 6 (2010), 345–379.Google Scholar
- Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIGMOD international conference on Management of data. AcM, 1247–1250.Google ScholarDigital Library
- Eric Brill, Jimmy J Lin, Michele Banko, Susan T Dumais, Andrew Y Ng, 2001. Data-Intensive Question Answering. In TREC, Vol. 56. 90.Google Scholar
- Andrew Carlson, Justin Betteridge, Bryan Kisiel, Burr Settles, Estevam R Hruschka Jr, and Tom M Mitchell. 2010. Toward an Architecture for Never-Ending Language Learning. In AAAI, Vol. 5. 3.Google Scholar
- Paolo Ferragina and Ugo Scaiella. 2012. Fast and accurate annotation of short texts with wikipedia pages. IEEE software 29, 1 (2012), 70–75.Google ScholarDigital Library
- Dihong Gong, Daisy Zhe Wang, and Yang Peng. 2017. Multimodal Learning for Web Information Extraction. In Proceedings of the 25th ACM International Conference on Multimedia (Mountain View, California, USA) (MM ’17). Association for Computing Machinery, New York, NY, USA, 288–296.Google ScholarDigital Library
- Morteza Shahriari Nia, Christan Grant, Yang Peng, Daisy Zhe Wang, and Milenko Petrovic. 2013. University of Florida Knowledge Base Acceleration Notebook. The Twenty-Second Text REtrieval Conference (TREC 2013) (2013).Google Scholar
- Morteza Shahriari Nia, Christan Earl Grant, Yang Peng, Daisy Zhe Wang, and Milenko Petrovic. 2014. Streaming Fact Extraction for Wikipedia Entities at Web-Scale. In FLAIRS Conference.Google Scholar
- Yang Peng. 2017. Multimodal Fusion: A Theory and Applications. University of Florida (2017).Google Scholar
- Yang Peng, Daisy Zhe Wang, Ishan Patwa, Dihong Gong, and Chunsheng Victor Fang. 2015. Probabilistic Ensemble Fusion for Multimodal Word Sense Disambiguation. In Multimedia (ISM), 2015 IEEE International Symposium on. IEEE, 172–177.Google ScholarCross Ref
- Yang Peng, Xiaofeng Zhou, Daisy Zhe Wang, and Chunsheng Victor Fang. 2016. Scalable image retrieval with multimodal fusion. In The Twenty-Ninth International Flairs Conference.Google Scholar
- Yang Peng, Xiaofeng Zhou, Daisy Zhe Wang, Ishan Patwa, Dihong Gong, and Chunsheng Fang. 2016. Multimodal Ensemble Fusion for Disambiguation and Retrieval. IEEE MultiMedia (2016).Google Scholar
- Wei Shen, Jianyong Wang, and Jiawei Han. 2015. Entity linking with a knowledge base: Issues, techniques, and solutions. IEEE Transactions on Knowledge and Data Engineering 27, 2 (2015), 443–460.Google ScholarCross Ref
- Fabian M Suchanek, Gjergji Kasneci, and Gerhard Weikum. 2007. Yago: a core of semantic knowledge. In Proceedings of the 16th international conference on World Wide Web. ACM, 697–706.Google ScholarDigital Library
- Huan Sun, Hao Ma, Wen-tau Yih, Chen-Tse Tsai, Jingjing Liu, and Ming-Wei Chang. 2015. Open domain question answering via semantic enrichment. In Proceedings of the 24th International Conference on World Wide Web. ACM, 1045–1055.Google ScholarDigital Library
- TagMe. 2018.. Retrieved 2018-10-12 from https://sobigdata.d4science.org/web/tagme/Google Scholar
- Ellen M Voorhees 1999. The TREC-8 Question Answering Track Report. In Trec, Vol. 99. 77–82.Google Scholar
- Robert West, Evgeniy Gabrilovich, Kevin Murphy, Shaohua Sun, Rahul Gupta, and Dekang Lin. 2014. Knowledge base completion via search-based question answering. In Proceedings of the 23rd international conference on World wide web. ACM, 515–526.Google ScholarDigital Library
- Yago. 2018.. Retrieved 2018-10-12 from https://www.mpi-inf.mpg.de/departments/databases-and-information-systems/research/yago-naga/yago/Google Scholar
- Ce Zhang. 2015. DeepDive: a data management system for automatic knowledge base construction. Madison, Wisconsin: University of Wisconsin-Madison (2015).Google Scholar
Index Terms
- Query-Driven Knowledge Graph Construction using Question Answering and Multimodal Fusion
Recommendations
Fusing Essential Knowledge for Text-Based Open-Domain Question Answering
Advances in Knowledge Discovery and Data MiningAbstractQuestion answering (QA) systems can be classified as either text-based QA systems or knowledge base QA (KBQA) systems, depending on the used knowledge source. KBQA systems are generally domain-specific and can’t deal with a variety of questions in ...
Knowledge Graph Question Answering with Ambiguous Query
WWW '23: Proceedings of the ACM Web Conference 2023Knowledge graph question answering aims to identify answers of the query according to the facts in the knowledge graph. In the vast majority of the existing works, the input queries are considered perfect and can precisely express the user’s query ...
Towards Knowledge Graph-Agnostic SPARQL Query Validation for Improving Question Answering
The Semantic Web: ESWC 2022 Satellite EventsAbstractA Knowledge Graph Question Answering (KGQA) system needs to generate a SPARQL query over a knowledge graph (KG) that is reflecting a user’s information need expressed by the given natural-language question. Yet, many of these generated queries ...
Comments