Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge Bases

V Thejas, Abhijeet Gupta, Sebastian Padó


Abstract
Collaboratively constructed knowledge bases play an important role in information systems, but are essentially always incomplete. Thus, a large number of models has been developed for Knowledge Base Completion, the task of predicting new attributes of entities given partial descriptions of these entities. Virtually all of these models either concentrate on numeric attributes (<Italy,GDP,2T$>) or they concentrate on categorical attributes (<Tim Cook,chairman,Apple>). In this paper, we propose a simple feed-forward neural architecture to jointly predict numeric and categorical attributes based on embeddings learned from textual occurrences of the entities in question. Following insights from multi-task learning, our hypothesis is that due to the correlations among attributes of different kinds, joint prediction improves over separate prediction. Our experiments on seven FreeBase domains show that this hypothesis is true of the two attribute types: we find substantial improvements for numeric attributes in the joint model, while performance remains largely unchanged for categorical attributes. Our analysis indicates that this is the case because categorical attributes, many of which describe membership in various classes, provide useful ‘background knowledge’ for numeric prediction, while this is true to a lesser degree in the inverse direction.
Anthology ID:
R19-1137
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
1194–1202
Language:
URL:
https://aclanthology.org/R19-1137
DOI:
10.26615/978-954-452-056-4_137
Bibkey:
Cite (ACL):
V Thejas, Abhijeet Gupta, and Sebastian Padó. 2019. Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge Bases. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 1194–1202, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge Bases (Thejas et al., RANLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/R19-1137.pdf