COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Language Technology Lab Seminars > Mapping Text to Knowledge Graph Entities with Multi-Sense LSTMs
Mapping Text to Knowledge Graph Entities with Multi-Sense LSTMsAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Edoardo Maria Ponti. This talk has been canceled/deleted Abstract: In this talk we address 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. Paper: http://aclweb.org/anthology/D18-1221 Code: https://bitbucket.org/dimkart/ms-lstm/ This talk is part of the Language Technology Lab Seminars series. This talk is included in these lists:This talk is not included in any other list Note that ex-directory lists are not shown. |
Other listsSimple Ideas that Change the World Baha'i Awareness Week CoSBi Computational and Systems Biology SeriesOther talksArt speak Christ's Climate seminar 4 Help! I need to find stuff for my project now! (Repeat session) The Humanitarian Club Lunchtime Talk: Dr Amanda Prorok |