Multilingual Open Relation Extraction Using Cross-lingual Projection
This work addresses the lack of multilingual capabilities in relation extraction systems, enabling broader language coverage for NLP applications.
The paper tackled the problem of open domain relation extraction being limited to English by proposing a cross-lingual annotation projection method, achieving results on three typologically different languages and releasing annotations and extracted relations for 61 languages from Wikipedia.
Open domain relation extraction systems identify relation and argument phrases in a sentence without relying on any underlying schema. However, current state-of-the-art relation extraction systems are available only for English because of their heavy reliance on linguistic tools such as part-of-speech taggers and dependency parsers. We present a cross-lingual annotation projection method for language independent relation extraction. We evaluate our method on a manually annotated test set and present results on three typologically different languages. We release these manual annotations and extracted relations in 61 languages from Wikipedia.