header

Domain Adaptation for Ontology Localization

24 Pages Posted: 27 Jun 2018 First Look: Accepted

See all articles by John McCrae

John McCrae

Bielefeld University - Cognitive Interaction Technology (CITEC); National University of Ireland, Galway (NUIG) - Insight Centre for Data Analytics

Mihael Arcan

National University of Ireland, Galway (NUIG) - Insight Centre for Data Analytics

Kartik Asooja

National University of Ireland, Galway (NUIG) - Insight Centre for Data Analytics; Universidad Politécnica de Madrid - Ontology Engineering Group

Jorge Gracia

Universidad Politécnica de Madrid - Ontology Engineering Group

Paul Buitelaar

National University of Ireland, Galway (NUIG) - Unit for Natural Language Processing

Philipp Cimiano

Bielefeld University - Semantic Computing Group

Abstract

Ontology localization is the task of adapting an ontology to a different cultural context, and has been identified as an important task in the context of the Multilingual Semantic Web vision. The key task in ontology localization is translating the lexical layer of an ontology, i.e., its labels, into some foreign language. For this task, we hypothesise that the translation quality can be improved by adapting a machine translation system to the domain of the ontology. To this end, we build on the success of existing statistical machine translation (SMT) approaches, and investigate the impact of different domain adaptation techniques on the task.

In particular, we investigate three techniques:

i) enriching a phrase table by domain-specific translation candidates acquired from existing Web resources,

ii) relying on Explicit Semantic Analysis as an additional technique for scoring a certain translation of a given source phrase, as well as

iii) adaptation of the language model by means of weighting n-grams with scores obtained from topic modelling. We present in detail the impact of each of these three techniques on the task of translating ontology labels. We show that these techniques have a generally positive effect on the quality of translation of the ontology and that, in combination, they provide a significant improvement in quality.

Keywords: ontology localization, statistical machine translation, domain adaptation

Suggested Citation

McCrae, John and Arcan, Mihael and Asooja, Kartik and Gracia, Jorge and Buitelaar, Paul and Cimiano, Philipp, Domain Adaptation for Ontology Localization (2016). Journal of Web Semantics First Look 36_0_2. Available at SSRN: https://ssrn.com/abstract=3199218 or http://dx.doi.org/10.2139/ssrn.3199218

John McCrae (Contact Author)

Bielefeld University - Cognitive Interaction Technology (CITEC) ( email )

Universitätsstraße 25
Bielefeld, 33613
Germany

National University of Ireland, Galway (NUIG) - Insight Centre for Data Analytics ( email )

The DERI Building IDA Business Park
Galway
Ireland

Mihael Arcan

National University of Ireland, Galway (NUIG) - Insight Centre for Data Analytics

The DERI Building IDA Business Park
Galway
Ireland

Kartik Asooja

National University of Ireland, Galway (NUIG) - Insight Centre for Data Analytics

The DERI Building IDA Business Park
Galway
Ireland

Universidad Politécnica de Madrid - Ontology Engineering Group

Madrid
Spain

Jorge Gracia

Universidad Politécnica de Madrid - Ontology Engineering Group

Madrid
Spain

Paul Buitelaar

National University of Ireland, Galway (NUIG) - Unit for Natural Language Processing ( email )

University Road
Galway
Ireland

Philipp Cimiano

Bielefeld University - Semantic Computing Group ( email )

Universitätsstraße 25
Bielefeld, 33613
Germany

Register to save articles to
your library

Register

Paper statistics

Abstract Views
112
Downloads
3