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.- Anthology ID:
- D18-1221
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1959–1970
- Language:
- URL:
- https://aclanthology.org/D18-1221
- DOI:
- 10.18653/v1/D18-1221
- Cite (ACL):
- Dimitri Kartsaklis, Mohammad Taher Pilehvar, and Nigel Collier. 2018. Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMs. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1959–1970, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMs (Kartsaklis et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/D18-1221.pdf
- Data
- Cora