TU Darmstadt / ULB / TUbiblio

End-to-end Representation Learning for Question Answering with Weak Supervision

Sorokin, Daniil and Gurevych, Iryna :
End-to-end Representation Learning for Question Answering with Weak Supervision.
[Online-Edition: https://link.springer.com/chapter/10.1007%2F978-3-319-69146-...]
In: Communications in Computer and Information Science , 769 . Springer, Cham
[Conference or Workshop Item] , (2017)

Official URL: https://link.springer.com/chapter/10.1007%2F978-3-319-69146-...

Abstract

In this paper we present a factoid question answering system for participation in Task 4 of the QALD-7 shared task. Our system is an end-to-end neural architecture for learning a semantic representation of the input question. It iteratively generates representations and uses a convolutional neural network (CNN) model to score them at each step. We take the semantic representation with the highest final score and execute it against Wikidata to retrieve the answers. We show on the Task 4 data set that our system is able to successfully generalize to new data.

Item Type: Conference or Workshop Item
Erschienen: 2017
Creators: Sorokin, Daniil and Gurevych, Iryna
Title: End-to-end Representation Learning for Question Answering with Weak Supervision
Language: English
Abstract:

In this paper we present a factoid question answering system for participation in Task 4 of the QALD-7 shared task. Our system is an end-to-end neural architecture for learning a semantic representation of the input question. It iteratively generates representations and uses a convolutional neural network (CNN) model to score them at each step. We take the semantic representation with the highest final score and execute it against Wikidata to retrieve the answers. We show on the Task 4 data set that our system is able to successfully generalize to new data.

Title of Book: Semantic Web Challenges: 4th SemWebEval Challenge at ESWC 2017
Series Name: Communications in Computer and Information Science
Volume: 769
Publisher: Springer, Cham
Uncontrolled Keywords: UKP_reviewed;UKP_p_QAEduInf;reviewed;UKP_a_DLinNLP;UKP_a_LSRA
Divisions: Department of Computer Science
Department of Computer Science > Ubiquitous Knowledge Processing
DFG-Graduiertenkollegs
DFG-Graduiertenkollegs > Research Training Group 1994 Adaptive Preparation of Information from Heterogeneous Sources
Event Location: Portoroz, Slovenia
Date Deposited: 23 May 2017 16:26
Official URL: https://link.springer.com/chapter/10.1007%2F978-3-319-69146-...
Identification Number: TUD-CS-2017-0113
Related URLs:
Export:

Optionen (nur für Redakteure)

View Item View Item