Using hyperlinks to improve multilingual partial parsers

Code

• bitbucket.org/soegaard/hyperlink-iwpt17
  OfficialIn papernone★ 0

Abstract

Syntactic annotation is costly and not available for the vast majority of the world's languages. We show that sometimes we can do away with less labeled data by exploiting more readily available forms of mark-up. Specifically, we revisit an idea from Valentin Spitkovsky's work (2010), namely that hyperlinks typically bracket syntactic constituents or chunks. We strengthen his results by showing that not only can hyperlinks help in low resource scenarios, exemplified here by Quechua, but learning from hyperlinks can also improve state-of-the-art NLP models for English newswire. We also present out-of-domain evaluation on English Ontonotes 4.0.

Tasks

Reproductions