Connectionist Transfer in Machine Translation
نویسندگان
چکیده
A traditional transfer system in machine translation maps between language structures and an intermediate representation. Our connectionist transfer system maps from f-structures of one language to f-structures of another language. It encodes the intermediate representation implicitly in neural networks' activation patterns. The system is learnable, therefore it does not need any e ort in hand-crafting the representation and mapping rules. Experiments show the system has good scalability and generalizability performance.
منابع مشابه
Dual-Coding Theory and Connectionist Lexical Selection
We introduce the bilingual dual-coding theory as a model for bilingual mental representation. Based on this model, lexical selection neural networks are implemented for a connectionist transfer project in machine translation.
متن کاملConnectionist F - structure Transfer
A traditional transfer system in machine translation maps between language structures and an intermediate representation. Our connectionist transfer system maps from f-structures of one language to f-structures of another language. It encodes the intermediate representation implicitly in neural networks' activation patterns. The system is learnable, therefore it does not need any e ort in handc...
متن کاملImprovements on Automatic Word Codification for Connectionist Machine Translation
Encouragingly accurate translations have recently been obtained using a connectionist translator called RECONTRA (Recurrent Connectionist Translator). In order to deal with tasks of medium or large vocabularies, distributed representations of the lexicons are required in this translator. A simple connectionist model has been recently designed to automatically obtain word distributed representat...
متن کاملA connectionist approach to machine translation
Connectionist Models can be considered as an encouraging approach to Example-Based Machine Translation. However, the neural translators developed in the literature are quite complex and require great human effort to classify and prepare training data. This paper presents an effective and more simple text-to-text connectionist translator with which translations from the source to the target lang...
متن کاملJANUS: Speech-to-Speech Translation Using Connectionist and Non-Connectionist Techniques
We present JANUS, a speech-to-speech translation system that utilizes diverse processing strategies, including connectionist learning, traditional AI knowledge representation approaches, dynamic programming, and stochastic techniques. JANUS translates continuously spoken English and German into German, English, and Japanese. JANUS currently achieves 87% translation fidelity from English speech ...
متن کامل