Learning Constituent Headedness

TL;DR

This paper introduces an explicit model for constituent headedness, improving syntactic analysis accuracy by learning head predictions directly from aligned constituency and dependency data, outperforming rule-based methods.

Contribution

It presents a supervised approach to predict constituent headedness as an explicit layer, enhancing parsing accuracy and cross-lingual transferability.

Findings

Achieves near-ceiling intrinsic accuracy on English and Chinese data.

Outperforms Collins-style rule-based percolation significantly.

Improves constituency-to-dependency conversion fidelity.

Abstract

Headedness is widely used as an organizing device in syntactic analysis, yet constituency treebanks rarely encode it explicitly and most processing pipelines recover it procedurally via percolation rules. We treat this notion of constituent headedness as an explicit representational layer and learn it as a supervised prediction task over aligned constituency and dependency annotations, inducing supervision by defining each constituent head as the dependency span head. On aligned English and Chinese data, the resulting models achieve near-ceiling intrinsic accuracy and substantially outperform Collins-style rule-based percolation. Predicted heads yield comparable parsing accuracy under head-driven binarization, consistent with the induced binary training targets being largely equivalent across head choices, while increasing the fidelity of deterministic constituency-to-dependency conversion and transferring across resources and languages under simple label-mapping interfaces.