KEIPD: Knowledge Extraction and Inference System for Personal Documents
Public personal documents on the Internet, such as resumes and personal homepages, may imply social relationships among people, which is of great value in various applications. This paper presents KEIPD, a system to extract and infer knowledge from personal documents. KEIPD employs a tree-similarity based approach to extract information from personal documents to obtain a relational network of entities. Then the inference of social relationships can be transformed into a link prediction problem. KEIPD implements some popular unsupervised predictors for link prediction and prune the candidate entity pairs based on the domain-dependent constraint.
KeywordsLink Prediction Parse Tree Name Entity Recognition Relational Network Path Query
- 1.Che, W., Li, Z., Liu, T.: LTP: a Chinese language technology platform. In: Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations. pp. 13–16. Association for Computational Linguistics (2010)Google Scholar
- 2.Davis, D., Lichtenwalter, R., Chawla, N.V.: Multi-relational link prediction in heterogeneous information networks. In: 2011 International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 281–288. IEEE (2011)Google Scholar
- 3.Zhang, M., Su, J., Wang, D., Zhou, G., Tan, C.-L.: Discovering relations between named entities from a large raw corpus using tree similarity-based clustering. In: Dale, R., Wong, K.-F., Su, J., Kwong, O.Y. (eds.) IJCNLP 2005. LNCS (LNAI), vol. 3651, pp. 378–389. Springer, Heidelberg (2005)CrossRefGoogle Scholar