From a Distance: Using Cross-lingual Word Alignments for Noun Compound Bracketing
Patrick Ziering, Lonneke van der Plas · 2015
We present a cross-lingual method for determining NP structures. More specifically, we try to determine whether the semantics of tripartite noun compounds in context requires a left or right branching interpretation. The system exploits the difference in word position between languages as found in parallel corpora. We achieve a bracketing accuracy of 94.6%, significantly outperforming all systems in comparison and comparable to human performance. Our system generates large amounts of high-quality bracketed NPs in a multilingual context that can be used to train supervised learners.