Statistical machine translation (SMT) should benefit from linguistic information to improve performance but current state-of-the-art models rely purely on data-driven models. There are several reasons why prior efforts to build linguistically annotated models have failed or not even been attempted. Firstly, the practical implementation often requires too much work to be cost effective. Where ad...

This paper presents an object-oriented model for machine translation based on Universal Grammar, the Universal Lexicon and language-specific grammars and the lexicons, and demonstrates the internal structures of these linguistic constructs by following a step-by-step process of English to Japanese translation. It elucidates what elements are required in the Universal Lexicon and the lexicons of...

The paper aims to assess the quality of English collaborative translation Rajaa Alsanea’s Arabian novel Girls Riyadh, focusing on linguistic and cultural features Target Text, a few which are sometimes nonexistent in Source Text. mixed literal/functional approach seems be inconsistent, observes, it is possibly due both apparent tension between self-translator her co-translator Marilyn Booth pro...

Verbmobil is a speaker-independent and bidirectional speech-to-speech translation system for spontaneous dialogs that can be accessed via GSM mobile phones. It handles dialogs in three business-oriented domains, with context-sensitive translation between four languages (English, German, Japanese, and Chinese). We show that in Verbmobil's multi-blackboard and multi-engine architecture the result...

I claim that an argument from the philosophy of statistics can be improved by using Carnapian inductive logic. \citet{GelmanShalizi2012} criticise a philosophical account of how statisticians ought to choose statistical models which they call `the received view of Bayesian inference' and propose a different account inspired by falsificationist philosophy of science. I introduce another philosop...