paper-with-me

홈 › Papers

Rationalization through Concepts

2021-05-11 · Findings (ACL) 2021 8 · Diego Antognini, Boi Faltings

Automated predictions require explanations to be interpretable by humans. One type of explanation is a rationale, i.e., a selection of input features such as relevant text snippets from which the model computes the outcome. However, a single overall selection does not provide a complete explanation, e.g., weighing several aspects for decisions. To this end, we present a novel self-interpretable model called ConRAT. Inspired by how human explanations for high-level decisions are often based on key concepts, ConRAT extracts a set of text snippets as concepts and infers which ones are described in the document. Then, it explains the outcome with a linear aggregation of concepts. Two regularizers drive ConRAT to build interpretable concepts. In addition, we propose two techniques to boost the rationale and predictive performance further. Experiments on both single- and multi-aspect sentiment classification tasks show that ConRAT is the first to generate concepts that align with human rationalization while using only the overall label. Further, it outperforms state-of-the-art methods trained on each aspect label independently.

📄 PDF Abstract BibTeX arXiv:2105.04837

Code (0)

등록된 구현이 없습니다.

Tasks

Sentiment AnalysisSentiment Classification

Similar Papers 제목 키워드 기반

Teaching and Critiquing Conceptualization and Operationalization in NLP

2025-12-20 · Vagrant Gautam arxiv

NLP researchers regularly invoke abstract concepts like "interpretability," "bias," "reasoning," and "stereotypes," without defining them. Each subfield has a shared understanding or conceptualization of what these terms…

Zero-Shot Rationalization by Multi-Task Transfer Learning from Question Answering

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Po-Nien Kung, Tse-Hsuan Yang, Yi-Cheng Chen, Sheng-Siang Yin 외

Extracting rationales can help human understand which information the model utilizes and how it makes the prediction towards better interpretability. However, annotating rationales requires much effort and only few datas…

Multi-Task LearningQuestion AnsweringTransfer Learning

Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows

2026-07-01 · Jalal Mahmud, Eser Kandogan arxiv

Large language models (LLMs) are increasingly used to generate queries, invoke tools, and construct analytical workflows. Although recent advances have substantially improved workflow generation and execution, the semant…

Boosting Explainability through Selective Rationalization in Pre-trained Language Models

2025-01-03 · Libing Yuan, Shuaibo Hu, Kui Yu, Le Wu

The widespread application of pre-trained language models (PLMs) in natural language processing (NLP) has led to increasing concerns about their explainability. Selective rationalization is a self-explanatory framework t…

Knowledge graphs for empirical concept retrieval

2024-04-10 · Lenka Tětková, Teresa Karen Scheidt, Maria Mandrup Fogh, Ellen Marie Gaunby Jørgensen 외

Concept-based explainable AI is promising as a tool to improve the understanding of complex models at the premises of a given user, viz.\ as a tool for personalized explainability. An important class of concept-based exp…

General KnowledgeKnowledge GraphsRetrieval