Learning Distributed Representations of Texts and Entities from Knowledge Base

Ikuya Yamada, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji


Abstract
We describe a neural network model that jointly learns distributed representations of texts and knowledge base (KB) entities. Given a text in the KB, we train our proposed model to predict entities that are relevant to the text. Our model is designed to be generic with the ability to address various NLP tasks with ease. We train the model using a large corpus of texts and their entity annotations extracted from Wikipedia. We evaluated the model on three important NLP tasks (i.e., sentence textual similarity, entity linking, and factoid question answering) involving both unsupervised and supervised settings. As a result, we achieved state-of-the-art results on all three of these tasks. Our code and trained models are publicly available for further academic research.
Anthology ID:
Q17-1028
Volume:
Transactions of the Association for Computational Linguistics, Volume 5
Month:
Year:
2017
Address:
Cambridge, MA
Editors:
Lillian Lee, Mark Johnson, Kristina Toutanova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
397–411
Language:
URL:
https://aclanthology.org/Q17-1028
DOI:
10.1162/tacl_a_00069
Bibkey:
Cite (ACL):
Ikuya Yamada, Hiroyuki Shindo, Hideaki Takeda, and Yoshiyasu Takefuji. 2017. Learning Distributed Representations of Texts and Entities from Knowledge Base. Transactions of the Association for Computational Linguistics, 5:397–411.
Cite (Informal):
Learning Distributed Representations of Texts and Entities from Knowledge Base (Yamada et al., TACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/Q17-1028.pdf
Code
 studio-ousia/ntee
Data
AIDA CoNLL-YAGOCoNLLSICKTAC 2010