Interpreting convolutional networks trained on textual data
원문 초록
There have been many advances in the artificial intelligence field due to the emergence of deep learning. In almost all sub-fields, artificial neural networks have reached or exceeded human-level performance. However, most of the models are not interpretable. As a result, it is hard to trust their decisions, especially in life and death scenarios. In recent years, there has been a movement toward creating explainable artificial intelligence, but most work to date has concentrated on image processing models, as it is easier for humans to perceive visual patterns. There has been little work in other fields like natural language processing. In this paper, we train a convolutional model on textual data and analyze the global logic of the model by studying its filter values. In the end, we find the most important words in our corpus to our models logic and remove the rest (95%). New models trained on just the 5% most important words can achieve the same performance as the original model while reducing training time by more than half. Approaches such as this will help us to understand NLP models, explain their decisions according to their word choices, and improve them by finding blind spots and biases.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Communicating Smartly in the Molecular Domain: Neural Networks in the Internet of Bio-Nano Things
midr: Learning from Black-Box Models by Maximum Interpretation Decomposition
Do Protein Transformers Have Biological Intelligence?
TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation
Addressing the Scarcity of Benchmarks for Graph XAI
Heart2Mind: Human-Centered Contestable Psychiatric Disorder Diagnosis System using Wearable ECG Monitors
토론
이 논문과 연결된 포럼 글이 아직 없습니다.