The Benefits of Label-Description Training for Zero-Shot Text Classification

• URL: http://arxiv.org/abs/2305.02239v2
• Date: Mon, 23 Oct 2023 15:24:57 GMT
• Title: The Benefits of Label-Description Training for Zero-Shot Text Classification
• Authors: Lingyu Gao, Debanjan Ghosh, Kevin Gimpel
• Abstract summary: Pretrained language models have improved zero-shot text classification. We propose a simple way to further improve zero-shot accuracies with minimal effort.
• Score: 35.27224341685012
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to further improve zero-shot accuracies with minimal effort. We curate small finetuning datasets intended to describe the labels for a task. Unlike typical finetuning data, which has texts annotated with labels, our data simply describes the labels in language, e.g., using a few related terms, dictionary/encyclopedia entries, and short templates. Across a range of topic and sentiment datasets, our method is more accurate than zero-shot by 17-19% absolute. It is also more robust to choices required for zero-shot classification, such as patterns for prompting the model to classify and mappings from labels to tokens in the model's vocabulary. Furthermore, since our data merely describes the labels but does not use input texts, finetuning on it yields a model that performs strongly on multiple text domains for a given label set, even improving over few-shot out-of-domain classification in multiple settings.

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)
• Substituting Data Annotation with Balanced Updates and Collective Loss in Multi-label Text Classification [19.592985329023733]
  Multi-label text classification (MLTC) is the task of assigning multiple labels to a given text. We study the MLTC problem in annotation-free and scarce-annotation settings in which the magnitude of available supervision signals is linear to the number of labels. Our method follows three steps, (1) mapping input text into a set of preliminary label likelihoods by natural language inference using a pre-trained language model, (2) calculating a signed label dependency graph by label descriptions, and (3) updating the preliminary label likelihoods with message passing along the label dependency graph.
  arXiv  Detail & Related papers  (2023-09-24T04:12:52Z)
• Description-Enhanced Label Embedding Contrastive Learning for Text Classification [65.01077813330559]
  Self-Supervised Learning (SSL) in model learning process and design a novel self-supervised Relation of Relation (R2) classification task. Relation of Relation Learning Network (R2-Net) for text classification, in which text classification and R2 classification are treated as optimization targets. external knowledge from WordNet to obtain multi-aspect descriptions for label semantic learning.
  arXiv  Detail & Related papers  (2023-06-15T02:19:34Z)
• Label Agnostic Pre-training for Zero-shot Text Classification [4.9081735096855565]
  In real-world applications, there exists an infinite label space for describing a given text. We introduce two new simple yet effective pre-training strategies, Implicit and Explicit pre-training. These methods inject aspect-level understanding into the model at train time with the goal of conditioning the model to build task-level understanding.
  arXiv  Detail & Related papers  (2023-05-25T22:55:32Z)
• 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)
• Unsupervised Ranking and Aggregation of Label Descriptions for Zero-Shot Classifiers [8.434227773463022]
  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.
  arXiv  Detail & Related papers  (2022-04-20T14:23:09Z)
• Label Semantic Aware Pre-training for Few-shot Text Classification [53.80908620663974]
  We propose Label Semantic Aware Pre-training (LSAP) to improve the generalization and data efficiency of text classification systems. LSAP incorporates label semantics into pre-trained generative models (T5 in our case) by performing secondary pre-training on labeled sentences from a variety of domains.
  arXiv  Detail & Related papers  (2022-04-14T17:33:34Z)
• Improving Probabilistic Models in Text Classification via Active Learning [0.0]
  We propose a fast new model for text classification that combines information from both labeled and unlabeled data with an active learning component. We show that by introducing information about the structure of unlabeled data and iteratively labeling uncertain documents, our model improves performance.
  arXiv  Detail & Related papers  (2022-02-05T20:09:26Z)
• 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)
• Text Classification Using Label Names Only: A Language Model Self-Training Approach [80.63885282358204]
  Current text classification methods typically require a good number of human-labeled documents as training data. We show that our model achieves around 90% accuracy on four benchmark datasets including topic and sentiment classification.
  arXiv  Detail & Related papers  (2020-10-14T17:06:41Z)

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.