Exploring the Use of Attention within an Neural Machine Translation Decoder States to Translate Idioms

2018/10/10 by Giancarlo Salton, Salton, Giancarlo D., Robert Ross +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1810.06695

openalex publication_date 2018/10/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Idioms pose problems to almost all Machine Translation systems. This type of language is very frequent in day-to-day language use and cannot be simply ignored. The recent interest in memory augmented models in the field of Language Modelling has aided the systems to achieve good results by bridging long-distance dependencies. In this paper we explore the use of such techniques into a Neural Machine Translation system to help in translation of idiomatic language.

Citations

• ADADELTA: An Adaptive Learning Rate Method
• Pointer Sentinel Mixture Models

Related

• Automatic Evaluation and Analysis of Idioms in Neural Machine Translation
• Examining the Tip of the Iceberg: A Data Set for Idiom Translation
• Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation
• Neural Machine Translation with Key-Value Memory-Augmented Attention
• An empirical analysis of phrase-based and neural machine translation