paper-with-me

홈 › Papers

CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations

2022-04-14 · ACL 2022 5 · Rakesh R Menon, Sayan Ghosh, Shashank Srivastava

Supervised learning has traditionally focused on inductive learning by observing labeled examples of a task. In contrast, humans have the ability to learn new concepts from language. Here, we explore training zero-shot classifiers for structured data purely from language. For this, we introduce CLUES, a benchmark for Classifier Learning Using natural language ExplanationS, consisting of a range of classification tasks over structured data along with natural language supervision in the form of explanations. CLUES consists of 36 real-world and 144 synthetic classification tasks. It contains crowdsourced explanations describing real-world tasks from multiple teachers and programmatically generated explanations for the synthetic tasks. To model the influence of explanations in classifying an example, we develop ExEnt, an entailment-based model that learns classifiers using explanations. ExEnt generalizes up to 18% better (relative) on novel tasks than a baseline that does not use explanations. We delineate key challenges for automated learning from explanations, addressing which can lead to progress on CLUES in the future. Code and datasets are available at: https://clues-benchmark.github.io.

📄 PDF Abstract BibTeX arXiv:2204.07142

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive Learning

Similar Papers 제목 키워드 기반

Training Classifiers with Natural Language Explanations

2018-05-10 · ACL 2018 7 · Braden Hancock, Paroma Varma, Stephanie Wang, Martin Bringmann 외

Training accurate classifiers requires many labels, but each label provides only limited information (one bit for binary classification). In this work, we propose BabbleLabble, a framework for training classifiers in whi…

Binary ClassificationGeneral ClassificationRelation Extraction

Let the CAT out of the bag: Contrastive Attributed explanations for Text

2021-09-16 · Saneem Chemmengath, Amar Prakash Azad, Ronny Luss, Amit Dhurandhar

Contrastive explanations for understanding the behavior of black box models has gained a lot of attention recently as they provide potential for recourse. In this paper, we propose a method Contrastive Attributed explana…

AttributeLanguage ModelingLanguage Modelling

Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering

2023-05-24 · Xingyu Fu, Ben Zhou, Sihao Chen, Mark Yatskar 외

Recent advances in multimodal large language models (LLMs) have shown extreme effectiveness in visual question answering (VQA). However, the design nature of these end-to-end models prevents them from being interpretable…

Question AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection

2022-05-01 · nlppower (ACL) 2022 5 · Giuseppe Attanasio, Debora Nozza, Eliana Pastor, Dirk Hovy

Transformer-based Natural Language Processing models have become the standard for hate speech detection. However, the unconscious use of these techniques for such a critical task comes with negative consequences. Various…

BenchmarkingHate Speech Detection

DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers

2024-10-29 · Rakesh R. Menon, Shashank Srivastava

Despite their high predictive accuracies, current machine learning systems often exhibit systematic biases stemming from annotation artifacts or insufficient support for certain classes in the dataset. Recent work propos…

Active Learningtext-classificationText Classification