Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many Classes

• URL: http://arxiv.org/abs/2410.05770v3
• Date: Mon, 21 Oct 2024 13:41:54 GMT
• Title: Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many Classes
• Authors: Tim Schopf, Alexander Blatzheim, Nektarios Machner, Florian Matthes,
• Abstract summary: FusionSent is an efficient and prompt-free approach for few-shot classification of scientific documents with many classes. Experiments show that FusionSent significantly outperforms strong baselines by an average of $6.0$ $F_1$label points.
• Score: 44.51779041553597
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific document classification is a critical task and often involves many classes. However, collecting human-labeled data for many classes is expensive and usually leads to label-scarce scenarios. Moreover, recent work has shown that sentence embedding model fine-tuning for few-shot classification is efficient, robust, and effective. In this work, we propose FusionSent (Fusion-based Sentence Embedding Fine-tuning), an efficient and prompt-free approach for few-shot classification of scientific documents with many classes. FusionSent uses available training examples and their respective label texts to contrastively fine-tune two different sentence embedding models. Afterward, the parameters of both fine-tuned models are fused to combine the complementary knowledge from the separate fine-tuning steps into a single model. Finally, the resulting sentence embedding model is frozen to embed the training instances, which are then used as input features to train a classification head. Our experiments show that FusionSent significantly outperforms strong baselines by an average of $6.0$ $F_{1}$ points across multiple scientific document classification datasets. In addition, we introduce a new dataset for multi-label classification of scientific documents, which contains 203,961 scientific articles and 130 classes from the arXiv category taxonomy. Code and data are available at https://github.com/sebischair/FusionSent.

Related papers

• Leveraging Semantic Segmentation Masks with Embeddings for Fine-Grained Form Classification [0.0]
  Efficient categorization of historical documents is crucial for fields such as genealogy, legal research and historical scholarship. We propose a representational learning strategy that integrates deep learning models such as ResNet, masked Image Transformer (Di), and embedding segmentation.
  arXiv  Detail & Related papers  (2024-05-23T04:28:50Z)
• Empowering Interdisciplinary Research with BERT-Based Models: An Approach Through SciBERT-CNN with Topic Modeling [0.0]
  This paper introduces a novel approach using the SciBERT model and CNNs to systematically categorize academic abstracts. The CNN uses convolution and pooling to enhance feature extraction and reduce dimensionality.
  arXiv  Detail & Related papers  (2024-04-16T05:21:47Z)
• Learning Section Weights for Multi-Label Document Classification [4.74495279742457]
  Multi-label document classification is a traditional task in NLP. We propose a new method called Learning Section Weights (LSW) LSW learns to assign weights to each section of, and incorporate the weights in the prediction.
  arXiv  Detail & Related papers  (2023-11-26T19:56:19Z)
• Many-Class Text Classification with Matching [65.74328417321738]
  We formulate textbfText textbfClassification as a textbfMatching problem between the text and the labels, and propose a simple yet effective framework named TCM. Compared with previous text classification approaches, TCM takes advantage of the fine-grained semantic information of the classification labels.
  arXiv  Detail & Related papers  (2022-05-23T15:51:19Z)
• MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information [47.44278057062421]
  We study the problem of weakly supervised text classification, which aims to classify text documents into a set of pre-defined categories with category surface names only. To be specific, we model the relationships between documents and metadata via a heterogeneous information network. We propose a novel framework, named MotifClass, which selects category-indicative motif instances, retrieves and generates pseudo-labeled training samples based on category names and indicative motif instances.
  arXiv  Detail & Related papers  (2021-11-07T07:39:10Z)
• Gated recurrent units and temporal convolutional network for multilabel classification [122.84638446560663]
  This work proposes a new ensemble method for managing multilabel classification. The core of the proposed approach combines a set of gated recurrent units and temporal convolutional neural networks trained with variants of the Adam gradients optimization approach.
  arXiv  Detail & Related papers  (2021-10-09T00:00:16Z)
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data [78.69828864672978]
  A central challenge in training classification models in the real-world federated system is learning with non-IID data. We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model. Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
  arXiv  Detail & Related papers  (2021-06-09T12:02:29Z)
• Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs [8.44680447457879]
  We present a simple multi-graph aggregation model that fuses knowledge from multiple label graphs encoding different semantic label relationships. We show that methods equipped with the multi-graph knowledge aggregation achieve significant performance improvement across almost all the measures on few/zero-shot labels.
  arXiv  Detail & Related papers  (2020-10-15T01:15:43Z)
• 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.