Leveraging RDF Graphs for Crossing Multiple Bilingual Dictionaries

Leveraging RDF Graphs for Crossing Multiple Bilingual Dictionaries Marta Villegas*, Maite Melero*, Jorge Gracia, Núria Bel* *Universitat Pompeu Fabra, Ontology Engineering Group, Universidad Politécnica de Madrid E-mail: marta.villegas@upf.edu, maite.melero@upf.edu, nuria.bel@upf.edu jgracia@fi.upm.es Abstract The experiments presented here exploit the properties of the Apertium RDF Graph, principally cycle density and nodes' degree, to automatically generate new translation relations between words, and therefore to enrich existing bilingual dictionaries with new entries. Currently, the Apertium RDF Graph includes data from 22 Apertium bilingual dictionaries and constitutes a large unified array of linked lexical entries and translations that are available and accessible on the Web (http://linguistic.linkeddata.es/apertium/). In particular, its graph structure allows for interesting exploitation opportunities, some of which are addressed in this paper. Two experiments are reported: in the first one, the original EN-ES translation set was removed from the Apertium RDF Graph and a new EN-ES version was generated. The results were compared against the previously removed EN-ES data and against the Concise Oxford Spanish Dictionary. In the second experiment, a new non-existent EN-FR translation set was generated. In this case the results were compared against a converted wiktionary English-French file. The results we got are really good and perform well for the extreme case of correlated polysemy. This led us to address the possibility to use cycles and nodes degree to identify potential oddities in the source data. If cycle density proves efficient when considering potential targets, we can assume that in dense graphs nodes with low degree may indicate potential errors. Keywords: Apertium,, LLOD, RDF/OWL, graphs, multilingual lexica, bilingual lexica, automatic lexical aquisition 1. Introduction The Apertium RDF Graph contains the RDF version of the Apertium 1 bilingual dictionaries (Forcada et al., 2011), which have been transformed into RDF and published on the Web following the Linked Data principles. As described by Gracia et al.. (2015), the core linguistic data of the Apertium RDF Graph was modeled using lemon, the LExicon Model for ONtologies (McCrae et al., 2012) while the translations between lexical entries used the lemon translation module (Gracia et al., 2014). Currently, the Apertium RDF Graph includes data from 22 Apertium bilingual dictionaries and it is expected that more Apertium data will be included in the near future. As result of the generation of the Apertium RDF Graph, a large unified array of linked lexical entries and translations is available and accessible on the Web (http://linguistic.linkeddata.es/apertium/). Its graph structure allows for interesting exploitation opportunities, some of them addressed in this paper. In particular, we propose a method to discover candidate translations for a given lexical entry and an algorithm to compute the confidence degree for such translations, based on the density exploration of the graph. The rest of the paper is organized as follows. In Section 2, related work on deriving bilingual lexical information from existent resources is discussed. Section 3 introduces our proposal for inferring indirect translations based on the exploration of the graph’s cycle density. The algorithm to compute a score for the cycles is presented in …

Content truncated to 500 words