NE-Table: A Neural key-value table for Named Entities (2018-04-22T00:00:00.000000Z)

TL;DR

This paper presents empirical evaluations on a structured Question-Answering task, three related Goal-Oriented dialog tasks, and a Reading-Comprehension task, which show that the proposed method can be effective in dealing with both in-vocabulary and OOV NEs.

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/

Authors

Jatin Ganhotra

4 papers

L. Polymenakos

4 papers

Janarthanan Rajendran

3 papers

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

TL;DR

Abstract

Authors

References25 items

Deep Contextualized Word Representations

Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning

Learning to Query, Reason, and Answer Questions On Ambiguous Texts

Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning

Learning End-to-End Goal-Oriented Dialog

Pointing the Unknown Words

Incorporating Copying Mechanism in Sequence-to-Sequence Learning

Neural Enquirer: Learning to Query Tables

Neural Programmer: Inducing Latent Programs with Gradient Descent

The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations

Improved Deep Learning Baselines for Ubuntu Corpus Dialogs

Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models

The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems

A Neural Conversational Model

End-To-End Memory Networks

Neural Responding Machine for Short-Text Conversation

The Stanford CoreNLP Natural Language Processing Toolkit

Distributed Representations of Words and Phrases and their Compositionality

To Link or Not to Link? A Study on End-to-End Tweet Entity Linking

Large-Scale Named Entity Disambiguation Based on Wikipedia Data

Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling

Long Short-Term Memory

2016) (they use match-type features for dealing with entities) and update the baseline model by using RNN encoding for sentences (similar to With-NETable)

Field of Study

Venue Information

Name

Type

URL

Alternate Names