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

April 22, 2018 · Entered Twilight · 🏛 Recent Advances in Natural Language Processing

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: CBT-OOV, LICENSE.txt, README.md, extended-bAbI-dialog-tasks

Authors Janarthanan Rajendran, Jatin Ganhotra, Xiaoxiao Guo, Mo Yu, Satinder Singh, Lazaros Polymenakos arXiv ID 1804.09540 Category cs.CL: Computation & Language Cross-listed cs.AI Citations 0 Venue Recent Advances in Natural Language Processing Repository https://github.com/IBM/ne-table-datasets ⭐ 2 Last Checked 2 months ago

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 available at - https://github.com/IBM/ne-table-datasets.