A Lexicalist Approach to the Translation of Colloquial Text

TL;DR

This paper introduces a lexicalist, fully automatic translation system for colloquial English, focusing on translating TV caption text into simple target sentences using a resource-based approach.

Contribution

It presents a novel large-scale multilingual translation system specifically designed for colloquial English, utilizing a lexicalist paradigm and addressing theoretical and implementation challenges.

Findings

Successfully translates colloquial English TV captions into Spanish.

Demonstrates the effectiveness of a lexicalist approach for colloquial language translation.

System is scalable and adaptable to multiple languages.

Abstract

Colloquial English (CE) as found in television programs or typical conversations is different than text found in technical manuals, newspapers and books. Phrases tend to be shorter and less sophisticated. In this paper, we look at some of the theoretical and implementational issues involved in translating CE. We present a fully automatic large-scale multilingual natural language processing system for translation of CE input text, as found in the commercially transmitted closed-caption television signal, into simple target sentences. Our approach is based on the Whitelock's Shake and Bake machine translation paradigm, which relies heavily on lexical resources. The system currently translates from English to Spanish with the translation modules for Brazilian Portuguese under development.