Visualizing and Understanding Neural Machine Translation
Citations
718 citations
Cites methods from "Visualizing and Understanding Neura..."
...We start by identifying the most important heads in each encoder layer using layer-wise relevance propagation (Ding et al., 2017)....
[...]
...Layer-wise relevance propagation (LRP) (Ding et al., 2017) is a method for computing the relative contribution of neurons at one point in a network to neurons at another....
[...]
442 citations
Cites background from "Visualizing and Understanding Neura..."
...The important or salient features can then be visualized in selected examples (Li et al., 2016a; Aubakirova and Bansal, 2016; Sundararajan et al., 2017; Arras et al., 2017a,b; Ding et al., 2017; Murdoch et al., 2018; Mudrakarta et al., 2018; Montavon et al., 2018; Godin et al., 2018)....
[...]
415 citations
398 citations
Cites background from "Visualizing and Understanding Neura..."
...There has also been work on visual evaluations of saliency maps (Li et al., 2016; Ding et al., 2017; Sundararajan et al., 2017)....
[...]
385 citations
References
73,978 citations
21,729 citations
20,027 citations
"Visualizing and Understanding Neura..." refers background or methods in this paper
...Figure 1: The attention-based encoder-decoder architecture for neural machine translation (Bahdanau et al., 2015)....
[...]
...Though projecting word embedding space into two dimensions (Faruqui and Dyer, 2014) and the attention matrix (Bahdanau et al., 2015) shed partial light on how NMT works, how to interpret the entire network still remains a challenge....
[...]
...Note that the attention mechanism (Bahdanau et al., 2015) is restricted to demonstrate the connection between words in source and target languages and unable to offer more insights in interpreting how target words are generated (see Section 4....
[...]
...We use the open-source toolkit GROUNDHOG (Bahdanau et al., 2015), which implements the attention-based encoder-decoder framework....
[...]
...In this work, we focus on the attention-based encoder-decoder framework (Bahdanau et al., 2015)....
[...]
19,998 citations
14,077 citations