Learning Syntax from Naturally-Occurring Bracketings
This work addresses syntactic parsing for natural language processing, but it is incremental as it builds on existing unsupervised methods with a new loss function.
The paper tackled the problem of unsupervised constituency parsing by using naturally-occurring bracketings as distant supervision, achieving an unlabeled F1 score of 68.9 on the English WSJ corpus.
Naturally-occurring bracketings, such as answer fragments to natural language questions and hyperlinks on webpages, can reflect human syntactic intuition regarding phrasal boundaries. Their availability and approximate correspondence to syntax make them appealing as distant information sources to incorporate into unsupervised constituency parsing. But they are noisy and incomplete; to address this challenge, we develop a partial-brackets-aware structured ramp loss in learning. Experiments demonstrate that our distantly-supervised models trained on naturally-occurring bracketing data are more accurate in inducing syntactic structures than competing unsupervised systems. On the English WSJ corpus, our models achieve an unlabeled F1 score of 68.9 for constituency parsing.