A Unified Understanding of Deep NLP Models for Text Classification

@article{Li2022AUU,
  title={A Unified Understanding of Deep NLP Models for Text Classification},
  author={Zhuguo Li and Xiting Wang and Weikai Yang and Jing Wu and Zhengyan Zhang and Zhiyuan Liu and Maosong Sun and Hui Zhang and Shixia Liu},
  journal={IEEE Transactions on Visualization and Computer Graphics},
  year={2022},
  volume={PP},
  pages={1-14}
}
The rapid development of deep natural language processing (NLP) models for text classification has led to an urgent need for a unified understanding of these models proposed individually. Existing methods cannot meet the need for understanding different models in one framework due to the lack of a unified measure for explaining both low-level (e.g., words) and high-level (e.g., phrases) features. We have developed a visual analysis tool, DeepNLPVis, to enable a unified understanding of NLP… 

Figures and Tables from this paper

Visual Analysis of Neural Architecture Spaces for Summarizing Design Principles

The key idea behind ArchExplorer is to make the architecture space explainable by exploiting structural distances between architectures by forming the pairwise distance calculation as solving an all-pairs shortest path problem.

References

SHOWING 1-10 OF 50 REFERENCES

Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models

The visualization, Attention Flows, is designed to support users in querying, tracing, and comparing attention within layers, across layers, and amongst attention heads in Transformer-based language models, and to help users gain insight on how a classification decision is made.

Visualizing and Understanding Neural Models in NLP

Four strategies for visualizing compositionality in neural models for NLP, inspired by similar work in computer vision, including LSTM-style gates that measure information flow and gradient back-propagation, are described.

Towards a Deep and Unified Understanding of Deep Neural Models in NLP

We define a unified information-based measure to provide quantitative explanations on how intermediate layers of deep Natural Language Processing (NLP) models leverage information of input words. Our

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

A Sentiment Treebank that includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality, and introduces the Recursive Neural Tensor Network.

Deep Contextualized Word Representations

A new type of deep contextualized word representation is introduced that models both complex characteristics of word use and how these uses vary across linguistic contexts, allowing downstream models to mix different types of semi-supervision signals.

Learning Structured Representation for Text Classification via Reinforcement Learning

Results show that the proposed reinforcement learning method can learn task-friendly representations by identifying important words or task-relevant structures without explicit structure annotations, and thus yields competitive performance.

Understanding Hidden Memories of Recurrent Neural Networks

This paper presents a visual analytics method for understanding and comparing RNN models for NLP tasks, and proposes a glyph-based sequence visualization based on aggregate information to analyze the behavior of an RNN’s hidden state at the sentence-level.

NLIZE: A Perturbation-Driven Visual Interrogation Tool for Analyzing and Interpreting Natural Language Inference Models

A visualization system that, through a tight yet flexible integration between visualization elements and the underlying model, allows a user to interrogate the model by perturbing the input, internal state, and prediction while observing changes in other parts of the pipeline.

The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models

The Language Interpretability Tool (LIT), an open-source platform for visualization and understanding of NLP models, is presented, which integrates local explanations, aggregate analysis, and counterfactual generation into a streamlined, browser-based interface to enable rapid exploration and error analysis.