Visualizing and Understanding Neural Machine Translation
نویسندگان
چکیده
While neural machine translation (NMT) has made remarkable progress in recent years, it is hard to interpret its internal workings due to the continuous representations and non-linearity of neural networks. In this work, we propose to use layer-wise relevance propagation (LRP) to compute the contribution of each contextual word to arbitrary hidden states in the attention-based encoderdecoder framework. We show that visualization with LRP helps to interpret the internal workings of NMT and analyze translation errors.
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 کاملVisualizing Neural Machine Translation Attention and Confidence
In this article, we describe a tool for visualizing the output and attention weights of neural machine translation systems and for estimating confidence about the output based on the attention. Our aim is to help researchers and developers better understand the behaviour of their NMT systems without the need for any reference translations. Our tool includes command line and web-based interfaces...
متن کاملEnabling Multi-Source Neural Machine Translation By Concatenating Source Sentences In Multiple Languages
In this paper, we propose a novel and elegant solution to “Multi-Source Neural Machine Translation” (MSNMT) which only relies on preprocessing a N-way multilingual corpus without modifying the Neural Machine Translation (NMT) architecture or training procedure. We simply concatenate the source sentences to form a single long multi-source input sentence while keeping the target side sentence as ...
متن کاملInteractive Visualization and Manipulation of Attention-based Neural Machine Translation
While neural machine translation (NMT) provides high-quality translation, it is still hard to interpret and analyze its behavior. We present an interactive interface for visualizing and intervening behavior of NMT, specifically concentrating on the behavior of beam search mechanism and attention component. The tool (1) visualizes search tree and attention and (2) provides interface to adjust se...
متن کاملInteractive Poster: The Chinese Room – Understanding and Correcting Machine Translation
We present an interface for visualizing information from a diverse type of linguistic resources to facilitate the correction of machine translated sentences. The goal of this project is to aid users with little or no fluency in the language of the original text to gain a greater comprehension of machine translations. This paper describes our interface and the linguistic resources it exploits to...
متن کامل