NE-Table: A Neural key-value table for Named Entities

Janarthanan Rajendran, Jatin Ganhotra, Xiaoxiao Guo, Mo Yu, Satinder Singh, Lazaros Polymenakos


Abstract
Many Natural Language Processing (NLP) tasks depend on using Named Entities (NEs) that are contained in texts and in external knowledge sources. While this is easy for humans, the present neural methods that rely on learned word embeddings may not perform well for these NLP tasks, especially in the presence of Out-Of-Vocabulary (OOV) or rare NEs. In this paper, we propose a solution for this problem, and present empirical evaluations on: a) a structured Question-Answering task, b) three related Goal-Oriented dialog tasks, and c) a Reading-Comprehension task, which show that the proposed method can be effective in dealing with both in-vocabulary and OOV NEs. We create extended versions of dialog bAbI tasks 1,2 and 4 and OOV versions of the CBT test set which are available at - https://github.com/IBM/ne-table-datasets/
Anthology ID:
R19-1114
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
980–993
Language:
URL:
https://www.aclweb.org/anthology/R19-1114
DOI:
10.26615/978-954-452-056-4_114
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/R19-1114.pdf