TRANSLATING

Translating Literary Types

Translating Neuralese

Several approaches have recently been proposed for learning decentralized deep multiagent policies that coordinate via a differentiable communication channel. While these policies are effective for many tasks, interpretation of their induced communication strategies has remained a challenge. Here we propose to interpret agents’ messages by translating them. Unlike in typical machine translation...

Translating Transliterations

Translating new entity names is important for improving performance in Natural Language Processing (NLP) applications such as Machine Translation (MT) and Cross Language Information Retrieval (CLIR). Usually, transliteration is used to obtain phonetic equivalents in a target language for a given source language word. However, transliteration across different writing systems often results in dif...

Translating Idioms

This paper discusses the t reatment of fixed word expressions developed for our ITS-2 FrenchEnglish translation system. This t reatment makes a clear distinction between compounds i.e. mult iword expressions of X°-level in which the chunks are adjacent and idiomatic phrases i.e. mult iword expressions of phrasal categories, where the chunks are not necessarily adjacent. In our system, compounds...

Translating Diagrams

Computer programs have to “understand” diagrams if diagrams are going to be used for communications with or through the computer, i.e., the computer has to be supplied with a method that translates a diagram into an abstract internal representation for further processing. This paper describes such a method that is based on a specification of the translation process. The translation process star...