Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Making Efficient Use of a Domain Expert's Time in Relation Extraction

 
: Adilova, Linara; Giesselbach, Sven; Rüping, Stefan

:
Fulltext urn:nbn:de:0011-n-5892231 (734 KByte PDF)
MD5 Fingerprint: 609bfaeb08b527e9eab7ed3d516d7cd9
Created on: 12.5.2020


Cellier, P.:
Workshop on Interactions between Data Mining and Natural Language Processing 2017. Proceedings. Online resource : Co-located with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2017), Skopje, Macedonia, September 22, 2017
Skopje, 2017 (CEUR Workshop Proceedings 1880)
http://ceur-ws.org/Vol-1880/
pp.1-16
Workshop on Interactions between Data Mining and Natural Language Processing <2017, Skopje>
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) <2017, Skopje>
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
031L0025C
English
Conference Paper, Electronic Publication
Fraunhofer IAIS ()
Corona

Abstract
Scarcity of labeled data is one of the most frequent problems faced in machine learning. This is particularly true in relation extraction in text mining, where large corpora of texts exists in many application domains, while labeling of text data requires an expert to invest much time to read the documents. Overall, state-of-the art models, like the convolutional neural network used in this paper, achieve great results when trained on large enough amounts of labeled data. However, from a practical point of view the question arises whether this is the most efficient approach when one takes the manual effort of the expert into account. In this paper, we report on an alternative approach where we first construct a relation extraction model using distant supervision, and only later make use of a domain expert to refine the results. Distant supervision provides a mean of labeling data given known relations in a knowledge base, but it suffers from noisy labeling. We introduce an active learning based extension, that allows our neural network to incorporate expert feedback and report on first results on a complex data set.

: http://publica.fraunhofer.de/documents/N-589223.html