Learning Parse and Translation Decisions From Examples With Rich Context

TL;DR

This paper introduces a machine learning-based system that uses rich contextual features to improve parsing and translation of natural language, demonstrated on Wall Street Journal sentences.

Contribution

It presents a novel decision-structure-based parser that leverages supervised parse action examples and extensive contextual information.

Findings

Effective parsing and translation on WSJ data

Utilizes rich morphological, syntactic, semantic features

Achieves deterministic shift-reduce parsing

Abstract

We present a knowledge and context-based system for parsing and translating natural language and evaluate it on sentences from the Wall Street Journal. Applying machine learning techniques, the system uses parse action examples acquired under supervision to generate a deterministic shift-reduce parser in the form of a decision structure. It relies heavily on context, as encoded in features which describe the morphological, syntactic, semantic and other aspects of a given parse state.