TASTY: Interactive Entity Linking As-You-Type

Sebastian Arnold, Robert Dziuba, Alexander Löser


Abstract
We introduce TASTY (Tag-as-you-type), a novel text editor for interactive entity linking as part of the writing process. Tasty supports the author of a text with complementary information about the mentioned entities shown in a ‘live’ exploration view. The system is automatically triggered by keystrokes, recognizes mention boundaries and disambiguates the mentioned entities to Wikipedia articles. The author can use seven operators to interact with the editor and refine the results according to his specific intention while writing. Our implementation captures syntactic and semantic context using a robust end-to-end LSTM sequence learner and word embeddings. We demonstrate the applicability of our system in English and German language for encyclopedic or medical text. Tasty is currently being tested in interactive applications for text production, such as scientific research, news editorial, medical anamnesis, help desks and product reviews.
Anthology ID:
C16-2024
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations
Month:
December
Year:
2016
Address:
Osaka, Japan
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
111–115
Language:
URL:
https://aclanthology.org/C16-2024
DOI:
Bibkey:
Cite (ACL):
Sebastian Arnold, Robert Dziuba, and Alexander Löser. 2016. TASTY: Interactive Entity Linking As-You-Type. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations, pages 111–115, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
TASTY: Interactive Entity Linking As-You-Type (Arnold et al., COLING 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/C16-2024.pdf