PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation

TL;DR

This paper introduces PENELOPIE, a method that uses neural machine translation to enable open information extraction for Greek by translating Greek to English, extracting data, and then back-translating.

Contribution

It presents a novel pipeline combining NMT and OIE techniques to improve information extraction in Greek, a low-resource language, outperforming existing methods.

Findings

Outperforms state-of-the-art Greek OIE methods

Effective NMT models for English-Greek translation

Successful back-translation of extracted triples

Abstract

In this paper we present our submission for the EACL 2021 SRW; a methodology that aims at bridging the gap between high and low-resource languages in the context of Open Information Extraction, showcasing it on the Greek language. The goals of this paper are twofold: First, we build Neural Machine Translation (NMT) models for English-to-Greek and Greek-to-English based on the Transformer architecture. Second, we leverage these NMT models to produce English translations of Greek text as input for our NLP pipeline, to which we apply a series of pre-processing and triple extraction tasks. Finally, we back-translate the extracted triples to Greek. We conduct an evaluation of both our NMT and OIE methods on benchmark datasets and demonstrate that our approach outperforms the current state-of-the-art for the Greek natural language.