Corpus-level and Concept-based Explanations for Interpretable Document Classification

• URL: http://arxiv.org/abs/2004.13003v4
• Date: Mon, 31 May 2021 03:22:08 GMT
• Title: Corpus-level and Concept-based Explanations for Interpretable Document Classification
• Authors: Tian Shi, Xuchao Zhang, Ping Wang, Chandan K. Reddy
• Abstract summary: We propose a corpus-level explanation approach to capture causal relationships between keywords and model predictions. We also propose a concept-based explanation method that can automatically learn higher-level concepts and their importance to model prediction tasks.
• Score: 23.194220621342254
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Using attention weights to identify information that is important for models' decision-making is a popular approach to interpret attention-based neural networks. This is commonly realized in practice through the generation of a heat-map for every single document based on attention weights. However, this interpretation method is fragile, and easy to find contradictory examples. In this paper, we propose a corpus-level explanation approach, which aims to capture causal relationships between keywords and model predictions via learning the importance of keywords for predicted labels across a training corpus based on attention weights. Based on this idea, we further propose a concept-based explanation method that can automatically learn higher-level concepts and their importance to model prediction tasks. Our concept-based explanation method is built upon a novel Abstraction-Aggregation Network, which can automatically cluster important keywords during an end-to-end training process. We apply these methods to the document classification task and show that they are powerful in extracting semantically meaningful keywords and concepts. Our consistency analysis results based on an attention-based Na\"ive Bayes classifier also demonstrate these keywords and concepts are important for model predictions.

Related papers

• Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery [52.498055901649025]
  Concept Bottleneck Models (CBMs) have been proposed to address the 'black-box' problem of deep neural networks. We propose a novel CBM approach -- called Discover-then-Name-CBM (DN-CBM) -- that inverts the typical paradigm. Our concept extraction strategy is efficient, since it is agnostic to the downstream task, and uses concepts already known to the model.
  arXiv  Detail & Related papers  (2024-07-19T17:50:11Z)
• Advancing Ante-Hoc Explainable Models through Generative Adversarial Networks [24.45212348373868]
  This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and makes use of adversarial training. This work presents a significant step towards building inherently interpretable deep vision models with task-aligned concept representations.
  arXiv  Detail & Related papers  (2024-01-09T16:16:16Z)
• Interpreting Pretrained Language Models via Concept Bottlenecks [55.47515772358389]
  Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. The lack of interpretability due to their black-box'' nature poses challenges for responsible implementation. We propose a novel approach to interpreting PLMs by employing high-level, meaningful concepts that are easily understandable for humans.
  arXiv  Detail & Related papers  (2023-11-08T20:41:18Z)
• Simple Mechanisms for Representing, Indexing and Manipulating Concepts [46.715152257557804]
  We will argue that learning a concept could be done by looking at its moment statistics matrix to generate a concrete representation or signature of that concept. When the concepts are intersected', signatures of the concepts can be used to find a common theme across a number of related intersected' concepts.
  arXiv  Detail & Related papers  (2023-10-18T17:54:29Z)
• Uncovering Unique Concept Vectors through Latent Space Decomposition [0.0]
  Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution estimates. We propose a novel post-hoc unsupervised method that automatically uncovers the concepts learned by deep models during training. Our experiments reveal that the majority of our concepts are readily understandable to humans, exhibit coherency, and bear relevance to the task at hand.
  arXiv  Detail & Related papers  (2023-07-13T17:21:54Z)
• Assessing Word Importance Using Models Trained for Semantic Tasks [0.0]
  We derive word significance from models trained to solve semantic task: Natural Language Inference and Paraphrase Identification. We evaluate their relevance using a so-called cross-task evaluation. Our method can be used to identify important words in sentences without any explicit word importance labeling in training.
  arXiv  Detail & Related papers  (2023-05-31T09:34:26Z)
• Unsupervised Keyphrase Extraction via Interpretable Neural Networks [27.774524511005172]
  Keyphrases that are most useful for predicting the topic of a text are important keyphrases. InSPECT is a self-explaining neural framework for identifying influential keyphrases. We show that INSPECT achieves state-of-the-art results in unsupervised key extraction across four diverse datasets.
  arXiv  Detail & Related papers  (2022-03-15T04:30:47Z)
• Resolving label uncertainty with implicit posterior models [71.62113762278963]
  We propose a method for jointly inferring labels across a collection of data samples. By implicitly assuming the existence of a generative model for which a differentiable predictor is the posterior, we derive a training objective that allows learning under weak beliefs.
  arXiv  Detail & Related papers  (2022-02-28T18:09:44Z)
• Active Refinement for Multi-Label Learning: A Pseudo-Label Approach [84.52793080276048]
  Multi-label learning (MLL) aims to associate a given instance with its relevant labels from a set of concepts. Previous works of MLL mainly focused on the setting where the concept set is assumed to be fixed. Many real-world applications require introducing new concepts into the set to meet new demands.
  arXiv  Detail & Related papers  (2021-09-29T19:17:05Z)
• Concept Learners for Few-Shot Learning [76.08585517480807]
  We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
  arXiv  Detail & Related papers  (2020-07-14T22:04:17Z)
• Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition [48.06319154279427]
  We present a method of instance-based learning that learns similarities between spans. Our method enables to build models that have high interpretability without sacrificing performance.
  arXiv  Detail & Related papers  (2020-04-29T23:32:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.