Prepositional Attachment Disambiguation Using Bilingual Parsing and Alignments

TL;DR

This paper presents a bilingual parsing approach using alignments and dual decomposition to improve prepositional phrase attachment accuracy in English, crucial for NLP tasks like machine translation.

Contribution

It introduces a novel dual decomposition algorithm that enforces agreement between English and Hindi parse trees for better PP attachment disambiguation.

Findings

10% improvement over baseline in attachment accuracy

Effective use of parallel data for syntactic disambiguation

Novel formulation for cross-lingual syntactic agreement

Abstract

In this paper, we attempt to solve the problem of Prepositional Phrase (PP) attachments in English. The motivation for the work comes from NLP applications like Machine Translation, for which, getting the correct attachment of prepositions is very crucial. The idea is to correct the PP-attachments for a sentence with the help of alignments from parallel data in another language. The novelty of our work lies in the formulation of the problem into a dual decomposition based algorithm that enforces agreement between the parse trees from two languages as a constraint. Experiments were performed on the English-Hindi language pair and the performance improved by 10% over the baseline, where the baseline is the attachment predicted by the MSTParser model trained for English.