Mapping text to knowledge graph entities using multi-sense LSTMs
Publication Date
2020-01-01Journal Title
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Conference Name
Empirical Methods in Natural Language Processing (EMNLP)
ISBN
9781948087841
Pages
1959-1970
Type
Conference Object
This Version
AM
Metadata
Show full item recordCitation
Kartsaklis, D., Pilehvar, M., & Collier, N. (2020). Mapping text to knowledge graph entities using multi-sense LSTMs. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018, 1959-1970. https://doi.org/10.17863/CAM.35220
Abstract
This paper addresses the problem of mapping natural language text to knowledge base entities. The mapping process is approached as a composition of a phrase or a sentence into a point in a multi-dimensional entity space obtained from a knowledge graph. The compositional model is an LSTM equipped with a dynamic disambiguation mechanism on the input word embeddings (a Multi-Sense LSTM), addressing polysemy issues. Further, the knowledge base space is prepared by collecting random walks from a graph enhanced with textual features, which act as a set of semantic bridges between text and knowledge base entities. The ideas of this work are demonstrated on large-scale text-to-entity mapping and entity classification tasks, with state of the art results.
Sponsorship
NVidia Corporation for the donation of a Titan XP GPU
Funder references
Engineering and Physical Sciences Research Council (EP/M005089/1)
Medical Research Council (MR/M025160/1)
Identifiers
External DOI: https://doi.org/10.17863/CAM.35220
This record's URL: https://www.repository.cam.ac.uk/handle/1810/287907
Rights
Licence:
http://www.rioxx.net/licenses/all-rights-reserved
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.