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

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.

arXiv commentRANLP 2019 - http://lml.bas.bg/ranlp2019/accepted.php . Datasets are available at - https://github.com/IBM/ne-table-datasets/

References in corpus (6)

• Distributed Representations of Words and Phrases and their Compositionality
• A Neural Conversational Model
• End-To-End Memory Networks
• The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
• End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
• Improved Deep Learning Baselines for Ubuntu Corpus Dialogs