Interactive Visualization and Manipulation of Attention-based Neural Machine Translation

By Jaesong Lee, Joong-Hwi Shin, Junseok Kim. 2017

84 citations recorded by the source corpus.

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 search tree and attention weight (manually or automatically) at real-time. We show the tool gives various methods to understand NMT.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Model Architectures

Citations in the corpus

Quantifying Attention Flow in Transformers (2020, background): “…the easiest and most popular approach to interpret a model’s decisions and to gain insights about its internals (Vaswani et al., 2017; Xu et al., 2015; Wang et al., 2016; Lee et al., 2017; Dehghani et al., 2019; Rockt¨aschel et al., 2016; Chen and Ji, 2019; Coenen et al., 2019; Clark et al., 2019).”
Is Attention Interpretable? (2019, methodology): “The existence of so much work on visualizing attention weights is a testament to attention’s popularity in this regard; to name just a few examples of these weights being examined to understand a model, recent work has focused on goals from explaining and debugging the current system’s decision (Lee”
Analyzing the Structure of Attention in a Transformer Language Model (2019, methodology): “, 2016) to bipartite graph representations (Liu et al., 2018; Lee et al., 2017; Strobelt et al., 2018).”
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness? (2020, background): “mechanisms have been considered as “inherently interpretable” (Ghaeini et al., 2018; Lee et al., 2017), recent work cast doubt regarding their faithfulness (Serrano and Smith, 2019; Jain and Wallace, 2019; Wiegreffe and Pinter, 2019).”
compare-mt: A Tool for Holistic Comparison of Language Generation Systems (2019, background): “…also been work that attempts to analyze the internal representations or alignments of phrase-based (DeNeefe et al., 2005; Weese and Callison-Burch, 2010) and neural (Ding et al., 2017; Lee et al., 2017) machine translation systems to attempt to understand why they arrived at the decisions they did.”
Behavioral Use Licensing for Responsible AI (2020, methodology): “Instead of building simpler ML methods to model the output of black-box neural networks, developers have done this by enabling visualizations of model components - such as heatmaps of words [39] or images [71].”
Attention in Natural Language Processing (2019, unknown): “instrumental in analyzing the outcome of neural networks, and a number of specific tools have been devised for such a visualization [12], [13].”
Seq2seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models (2018, unknown): “[25] who show a basic prototype to manipulate these parts of a model.”
Saliency-driven Word Alignment Interpretation for Neural Machine Translation (2019, background): “To the best of our knowledge, Li et al. (2016) presented the only work that directly employs saliency methods to interpret NLP models.”