Concept Equalization to Guide Correct Training of Neural Machine Translation
نویسندگان
چکیده
Neural machine translation decoders are usually conditional language models to sequentially generate words for target sentences. This approach is limited to find the best word composition and requires help of explicit methods as beam search. To help learning correct compositional mechanisms in NMTs, we propose concept equalization using direct mapping distributed representations of source and target sentences. In a translation experiment from English to French, the concept equalization significantly improved translation quality by 3.00 BLEU points compared to a state-of-the-art NMT model.
منابع مشابه
A Comparative Study of English-Persian Translation of Neural Google Translation
Many studies abroad have focused on neural machine translation and almost all concluded that this method was much closer to humanistic translation than machine translation. Therefore, this paper aimed at investigating whether neural machine translation was more acceptable in English-Persian translation in comparison with machine translation. Hence, two types of text were chosen to be translated...
متن کاملOutlier Detection Using Extreme Learning Machines Based on Quantum Fuzzy C-Means
One of the most important concerns of a data miner is always to have accurate and error-free data. Data that does not contain human errors and whose records are full and contain correct data. In this paper, a new learning model based on an extreme learning machine neural network is proposed for outlier detection. The function of neural networks depends on various parameters such as the structur...
متن کاملMachine Translation using Quantum Neural Network for Simple Sentences
This paper presents the machine translation system (MTS) which is based on the concept of self learning of semantically correct corpus using pattern recognition. The self learning process using pattern recognition is based on Quantum Neural Network (QNN). This is a novel and new approach to recognize and learn the corpus pattern using QNN. The paper 9ppresents systematically structure of the sy...
متن کاملReinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback
Machine translation is a natural candidate problem for reinforcement learning from human feedback: users provide quick, dirty ratings on candidate translations to guide a system to improve. Yet, current neural machine translation training focuses on expensive human-generated reference translations. We describe a reinforcement learning algorithm that improves neural machine translation systems f...
متن کاملTowards Proof Synthesis Guided by Neural Machine Translation for Intuitionistic Propositional Logic
Inspired by the recent evolution of deep neural networks (DNNs) in machine learning, we explore their application to PL-related topics. This paper is the first step towards this goal; we propose a proofsynthesis method for the negation-free propositional logic in which we use a DNN to obtain a guide of proof search. The idea is to view the proof-synthesis problem as a translation from a proposi...
متن کامل