Unsupervised Ranking and Aggregation of Label Descriptions for Zero-Shot Classifiers

• URL: http://arxiv.org/abs/2204.09481v1
• Date: Wed, 20 Apr 2022 14:23:09 GMT
• Title: Unsupervised Ranking and Aggregation of Label Descriptions for Zero-Shot Classifiers
• Authors: Angelo Basile, Marc Franco-Salvador and Paolo Rosso
• Abstract summary: In a true zero-shot setup, designing good label descriptions is challenging because no development set is available. We look at how probabilistic models of repeated rating analysis can be used for selecting the best label descriptions in an unsupervised fashion.
• Score: 8.434227773463022
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Zero-shot text classifiers based on label descriptions embed an input text and a set of labels into the same space: measures such as cosine similarity can then be used to select the most similar label description to the input text as the predicted label. In a true zero-shot setup, designing good label descriptions is challenging because no development set is available. Inspired by the literature on Learning with Disagreements, we look at how probabilistic models of repeated rating analysis can be used for selecting the best label descriptions in an unsupervised fashion. We evaluate our method on a set of diverse datasets and tasks (sentiment, topic and stance). Furthermore, we show that multiple, noisy label descriptions can be aggregated to boost the performance.

Related papers

• Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions [50.92702206798324]
  We propose a generative prompting framework for zero-shot text classification. GEN-Z measures the LM likelihood of input text conditioned on natural language descriptions of labels. We show that zero-shot classification with simple contextualization of the data source consistently outperforms both zero-shot and few-shot baselines.
  arXiv  Detail & Related papers  (2023-11-13T07:12:57Z)
• Don't Waste a Single Annotation: Improving Single-Label Classifiers Through Soft Labels [7.396461226948109]
  We address the limitations of the common data annotation and training methods for objective single-label classification tasks. Our findings indicate that additional annotator information, such as confidence, secondary label and disagreement, can be used to effectively generate soft labels.
  arXiv  Detail & Related papers  (2023-11-09T10:47:39Z)
• Rank-Aware Negative Training for Semi-Supervised Text Classification [3.105629960108712]
  Semi-supervised text classification-based paradigms (SSTC) typically employ the spirit of self-training. This paper presents a Rank-aware Negative Training (RNT) framework to address SSTC in learning with noisy label manner.
  arXiv  Detail & Related papers  (2023-06-13T08:41:36Z)
• Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations [91.67511167969934]
  imprecise label learning (ILL) is a framework for the unification of learning with various imprecise label configurations. We demonstrate that ILL can seamlessly adapt to partial label learning, semi-supervised learning, noisy label learning, and, more importantly, a mixture of these settings.
  arXiv  Detail & Related papers  (2023-05-22T04:50:28Z)
• The Benefits of Label-Description Training for Zero-Shot Text Classification [35.27224341685012]
  Pretrained language models have improved zero-shot text classification. We propose a simple way to further improve zero-shot accuracies with minimal effort.
  arXiv  Detail & Related papers  (2023-05-03T16:19:31Z)
• Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification [85.76130799062379]
  We study how false negative labels affect the model's explanation. We propose to boost the attribution scores of the model trained with partial labels to make its explanation resemble that of the model trained with full labels.
  arXiv  Detail & Related papers  (2023-04-04T14:00:59Z)
• Empowering Sentence Encoders with Prompting and Label Retrieval for Zero-shot Text Classification [5.484132137132862]
  Our framework, RaLP, encodes prompted label candidates with a sentence encoder, then assigns the label whose prompt embedding has the highest similarity with the input text embedding. RaLP achieves competitive or stronger performance than much larger baselines on various closed-set classification and multiple-choice QA datasets.
  arXiv  Detail & Related papers  (2022-12-20T16:18:03Z)
• Learning from Multiple Noisy Partial Labelers [8.357801312689618]
  Programmatic weak supervision creates models without hand-labeled training data by combining the outputs of noisy, user-written rules and other labelers. We introduce this capability by defining a probabilistic generative model that can estimate the underlying accuracies of multiple noisy partial labelers. We show how to scale up learning to 100k examples in one minute, a 300X speed up compared to a naive implementation.
  arXiv  Detail & Related papers  (2021-06-08T17:12:16Z)
• Unsupervised Label Refinement Improves Dataless Text Classification [48.031421660674745]
  Dataless text classification is capable of classifying documents into previously unseen labels by assigning a score to any document paired with a label description. While promising, it crucially relies on accurate descriptions of the label set for each downstream task. This reliance causes dataless classifiers to be highly sensitive to the choice of label descriptions and hinders the broader application of dataless classification in practice.
  arXiv  Detail & Related papers  (2020-12-08T03:37:50Z)
• A Study on the Autoregressive and non-Autoregressive Multi-label Learning [77.11075863067131]
  We propose a self-attention based variational encoder-model to extract the label-label and label-feature dependencies jointly. Our model can therefore be used to predict all labels in parallel while still including both label-label and label-feature dependencies.
  arXiv  Detail & Related papers  (2020-12-03T05:41:44Z)
• Exploiting Context for Robustness to Label Noise in Active Learning [47.341705184013804]
  We address the problems of how a system can identify which of the queried labels are wrong and how a multi-class active learning system can be adapted to minimize the negative impact of label noise. We construct a graphical representation of the unlabeled data to encode these relationships and obtain new beliefs on the graph when noisy labels are available. This is demonstrated in three different applications: scene classification, activity classification, and document classification.
  arXiv  Detail & Related papers  (2020-10-18T18:59:44Z)

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.