A Discourse-based Approach in Text-based Machine Translation

TL;DR

This paper introduces a discourse-based theoretical method for resolving ellipses in machine translation by transforming texts into primitive discourses, aiming to improve translation accuracy.

Contribution

It proposes a novel discourse formula application for ellipsis resolution and explores new primitive discourse patterns in text processing.

Findings

Discourse formula effectively resolves ellipses in newspaper texts.

Transformation into primitive discourses aids in understanding complex sentences.

Further refinement needed in dissection procedures for better primitive discourse discovery.

Abstract

This paper presents a theoretical research based approach to ellipsis resolution in machine translation. The formula of discourse is applied in order to resolve ellipses. The validity of the discourse formula is analyzed by applying it to the real world text, i.e., newspaper fragments. The source text is converted into mono-sentential discourses where complex discourses require further dissection either directly into primitive discourses or first into compound discourses and later into primitive ones. The procedure of dissection needs further improvement, i.e., discovering as many primitive discourse forms as possible. An attempt has been made to investigate new primitive discourses or patterns from the given text.