Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Learning Distributed Representations of Texts and Entities from Knowledge Base

About

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.

Ikuya Yamada, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji• 2017

Related benchmarks

TaskDatasetResultRank
Sentence RelatednessSTS 2014
News Spearman0.69
30
Factoid Question AnsweringHistory factoid QA (test)
Accuracy94.7
25
Entity LinkingTAC-KBP 2010 (test)
Accuracy87.7
16
Factoid Question AnsweringQuiz Bowl Literature category
Accuracy95.1
16
Named Entity DisambiguationTAC 2010
Micro Accuracy87.7
12
Semantic RelatednessSICK
Pearson r0.73
12
Entity LinkingCoNLL (test)
Micro Accuracy94.7
11
Factoid Question AnsweringLiterature factoid QA (test)
Accuracy95.1
9
Entity LinkingCoNLL-Aida (test)
Accuracy94.3
8
Entity DisambiguationCoNLL table P (test)
Accuracy94.3
7
Showing 10 of 10 rows

Other info

Code

Follow for update