We can still parse using syntactic rules

TL;DR

This paper presents a new syntactic parsing approach combining CFG and GPSG principles, capable of generating dependency and constituency trees, handling noise, and providing multiple hypotheses for improved accuracy.

Contribution

It introduces a novel parsing algorithm and syntactic rules that overcome CFG limitations and integrate theoretical syntactic work into practical NLP applications.

Findings

Achieved an average UAS of 54.5% on development data

Generated multiple parse hypotheses for reranking

Demonstrated applicability across diverse corpora

Abstract

This research introduces a new parsing approach, based on earlier syntactic work on context free grammar (CFG) and generalized phrase structure grammar (GPSG). The approach comprises both a new parsing algorithm and a set of syntactic rules and features that overcome the limitations of CFG. It also generates both dependency and constituency parse trees, while accommodating noise and incomplete parses. The system was tested on data from Universal Dependencies, showing a promising average Unlabeled Attachment Score (UAS) of 54.5% in the development dataset (7 corpora) and 53.8% in the test set (12 corpora). The system also provides multiple parse hypotheses, allowing further reranking to improve parsing accuracy. This approach also leverages much of the theoretical syntactic work since the 1950s to be used within a computational context. The application of this approach provides a transparent and interpretable NLP model to process language input.