paper-with-me

홈 › Papers

Regularization, Semi-supervision, and Supervision for a Plausible Attention-Based Explanation

2025-01-22 · Duc Hau Nguyen, Cyrielle Mallart, Guillaume Gravier, Pascale Sébillot

Attention mechanism is contributing to the majority of recent advances in machine learning for natural language processing. Additionally, it results in an attention map that shows the proportional influence of each input in its decision. Empirical studies postulate that attention maps can be provided as an explanation for model output. However, it is still questionable to ask whether this explanation helps regular people to understand and accept the model output (the plausibility of the explanation). Recent studies show that attention weights in the RNN encoders are hardly plausible because they spread on input tokens. We thus propose 3 additional constraints to the learning objective function to improve the plausibility of the attention map: regularization to increase the attention weight sparsity, semi-supervision to supervise the map by a heuristic and supervision by human annotation. Results show that all techniques can improve the attention map plausibility at some level. We also observe that specific instructions for human annotation might have a negative effect on classification performance. Beyond the attention map, the result of experiments on text classification tasks also shows that no matter how the constraint brings the gain, the contextualization layer plays a crucial role in finding the right space for finding plausible tokens.

📄 PDF Abstract BibTeX arXiv:2501.12775

Code (1)

kihansi95/linkmedia_attentionplausibilitybyconstraint 공식 구현 pytorch

Tasks

text-classificationText Classification

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

CFCG: Semi-Supervised Semantic Segmentation via Cross-Fusion and Contour Guidance Supervision

2023-01-01 · ICCV 2023 1 · Shuo Li, Yue He, Weiming Zhang , Wei zhang 외

Current state-of-the-art semi-supervised semantic segmentation (SSSS) methods typically adopt pseudo labeling and consistency regularization between multiple learners with different perturbations. Although the perfor…

Semantic SegmentationSemi-Supervised Semantic Segmentation

Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations

2023-05-24 · Wenting Zhao, Justin T. Chiu, Claire Cardie, Alexander M. Rush

Abductive reasoning aims to find plausible explanations for an event. This style of reasoning is critical for commonsense tasks where there are often multiple plausible explanations. Existing approaches for abductive rea…

C$^3$PS: Context-aware Conditional Cross Pseudo Supervision for Semi-supervised Medical Image Segmentation

2023-06-14 · Peng Liu, Guoyan Zheng

Semi-supervised learning (SSL) methods, which can leverage a large amount of unlabeled data for improved performance, has attracted increasing attention recently. In this paper, we introduce a novel Context-aware Conditi…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation+1

ARNOR: Attention Regularization based Noise Reduction for Distant Supervision Relation Classification

2019-07-01 · ACL 2019 7 · Wei Jia, Dai Dai, Xinyan Xiao, Hua Wu

Distant supervision is widely used in relation classification in order to create large-scale training data by aligning a knowledge base with an unlabeled corpus. However, it also introduces amounts of noisy labels where …

ClassificationGeneral ClassificationRelationRelation Classification+1

NanoNet: Parameter-Efficient Learning with Label-Scarce Supervision for Lightweight Text Mining Model

2026-02-05 · Qianren Mao, Yashuo Luo, Ziqi Qin, Junnan Liu 외 arxiv

The lightweight semi-supervised learning (LSL) strategy provides an effective approach of conserving labeled samples and minimizing model inference costs. Prior research has effectively applied knowledge transfer learnin…

Knowledge DistillationTransfer Learning