TU Darmstadt / ULB / TUbiblio

End-to-End Non-Factoid Question Answering with an Interactive Visualization of Neural Attention Weights

Rücklé, Andreas and Gurevych, Iryna (2017):
End-to-End Non-Factoid Question Answering with an Interactive Visualization of Neural Attention Weights.
In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics-System Demonstrations (ACL 2017), Association for Computational Linguistics, Vancouver, Canada, 4: System Demonstrations, [Online-Edition: http://aclweb.org/anthology/P17-4004],
[Conference or Workshop Item]

Abstract

Advanced attention mechanisms are an important part of successful neural network approaches for non-factoid answer selection because they allow the models to focus on few important segments within rather long answer texts. Analyzing attention mechanisms is thus crucial for understanding strengths and weaknesses of particular models. We present an extensible, highly modular service architecture that enables the transformation of neural network models for non-factoid answer selection into fully featured end-to-end question answering systems. The primary objective  of our system is to enable researchers a way to interactively explore and compare attention-based neural networks for answer selection. Our interactive user interface helps researchers to better understand the capabilities of the different approaches and can aid qualitative analyses.

Item Type: Conference or Workshop Item
Erschienen: 2017
Creators: Rücklé, Andreas and Gurevych, Iryna
Title: End-to-End Non-Factoid Question Answering with an Interactive Visualization of Neural Attention Weights
Language: English
Abstract:

Advanced attention mechanisms are an important part of successful neural network approaches for non-factoid answer selection because they allow the models to focus on few important segments within rather long answer texts. Analyzing attention mechanisms is thus crucial for understanding strengths and weaknesses of particular models. We present an extensible, highly modular service architecture that enables the transformation of neural network models for non-factoid answer selection into fully featured end-to-end question answering systems. The primary objective  of our system is to enable researchers a way to interactively explore and compare attention-based neural networks for answer selection. Our interactive user interface helps researchers to better understand the capabilities of the different approaches and can aid qualitative analyses.

Title of Book: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics-System Demonstrations (ACL 2017)
Volume: 4: System Demonstrations
Publisher: Association for Computational Linguistics
Uncontrolled Keywords: UKP_a_DLinNLP;UKP_p_QAEduInf
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Event Location: Vancouver, Canada
Date Deposited: 03 Apr 2017 09:58
Official URL: http://aclweb.org/anthology/P17-4004
Identification Number: TUD-CS-2017-0078
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item