Explaining Relation Classification Models with Semantic Extents
In recent years, the development of large pretrained language models, such as BERT and GPT, significantly improved information extraction systems on various tasks, including relation classification. State-of-the-art systems are highly accurate on scientific benchmarks. A lack of explainability is currently a complicating factor in many real-world applications. Comprehensible systems are necessary to prevent biased, counterintuitive, or harmful decisions. We introduce semantic extents, a concept to analyze decision patterns for the relation classification task. Semantic extents are the most influential parts of texts concerning classification decisions. Our definition allows similar procedures to determine semantic extents for humans and models. We provide an annotation tool and a software framework to determine semantic extents for humans and models conveniently and reproducibly. Comparing both reveals that models tend to learn shortcut patterns from data. These patterns are hard to detect with current interpretability methods, such as input reductions. Our approach can help detect and eliminate spurious decision patterns during model development. Semantic extents can increase the reliability and security of natural language processing systems. Semantic extents are an essential step in enabling applications in critical areas like healthcare or finance. Moreover, our work opens new research directions for developing methods to explain deep learning models.
Code (2)
Tasks
ClassificationRelationRelation ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Class-aware Information for Logit-based Knowledge Distillation
Knowledge distillation aims to transfer knowledge to the student model by utilizing the predictions/features of the teacher model, and feature-based distillation has recently shown its superiority over logit-based distil…
Knowledge DistillationOmniGraph: Rich Representation and Graph Kernel Learning
OmniGraph, a novel representation to support a range of NLP classification tasks, integrates lexical items, syntactic dependencies and frame semantic parses into graphs. Feature engineering is folded into the learning th…
Feature EngineeringGeneral ClassificationLISA: Explaining Recurrent Neural Network Judgments via Layer-wIse Semantic Accumulation and Example to Pattern Transformation
Recurrent neural networks (RNNs) are temporal networks and cumulative in nature that have shown promising results in various natural language processing tasks. Despite their success, it still remains a challenge to under…
Decision MakingRelation Classificationslot-fillingSlot FillingPARN: Position-Aware Relation Networks for Few-Shot Learning
Few-shot learning presents a challenge that a classifier must quickly adapt to new classes that do not appear in the training set, given only a few labeled examples of each new class. This paper proposes a position-aware…
Few-Shot LearningPositionRelationRelational Reasoning+1Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification
With the popularity of deep neural networks (DNNs), model interpretability is becoming a critical concern. Many approaches have been developed to tackle the problem through post-hoc analysis, such as explaining how predi…
ClassificationDisentanglementimage-classificationImage Classification