A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification

• URL: http://arxiv.org/abs/2501.13598v1
• Date: Thu, 23 Jan 2025 12:06:33 GMT
• Title: A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification
• Authors: Younes Yousef, Lukas Galke, Ansgar Scherp,
• Abstract summary: We introduce an effective hierarchical text classification architecture based on an off-the-shelf RoBERTa transformer. Unlike existing approaches for hierarchical text classification, the encoder of RADAr has no explicit encoding of the label hierarchy. Our experiments show that neither the label semantics nor an explicit graph encoder for the hierarchy is needed.
• Score: 6.704529554100875
• License:
• Abstract: Recent approaches in hierarchical text classification (HTC) rely on the capabilities of a pre-trained transformer model and exploit the label semantics and a graph encoder for the label hierarchy. In this paper, we introduce an effective hierarchical text classifier RADAr (Transformer-based Autoregressive Decoder Architecture) that is based only on an off-the-shelf RoBERTa transformer to process the input and a custom autoregressive decoder with two decoder layers for generating the classification output. Thus, unlike existing approaches for HTC, the encoder of RADAr has no explicit encoding of the label hierarchy and the decoder solely relies on the label sequences of the samples observed during training. We demonstrate on three benchmark datasets that RADAr achieves results competitive to the state of the art with less training and inference time. Our model consistently performs better when organizing the label sequences from children to parents versus the inverse, as done in existing HTC approaches. Our experiments show that neither the label semantics nor an explicit graph encoder for the hierarchy is needed. This has strong practical implications for HTC as the architecture has fewer requirements and provides a speed-up by a factor of 2 at inference time. Moreover, training a separate decoder from scratch in conjunction with fine-tuning the encoder allows future researchers and practitioners to exchange the encoder part as new models arise. The source code is available at https://github.com/yousef-younes/RADAr.

Related papers

• Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation [54.23510028456082]
  We propose a Triple-view Knowledge Distillation framework, termed TriKD, for semi-supervised semantic segmentation. The framework includes the triple-view encoder and the dual-frequency decoder.
  arXiv  Detail & Related papers  (2023-09-22T01:02:21Z)
• Hierarchical Verbalizer for Few-Shot Hierarchical Text Classification [10.578682558356473]
  hierarchical text classification (HTC) suffers a poor performance when low-resource or few-shot settings are considered. In this work, we propose the hierarchical verbalizer ("HierVerb"), a multi-verbalizer framework treating HTC as a single- or multi-label classification problem. In this manner, HierVerb fuses label hierarchy knowledge into verbalizers and remarkably outperforms those who inject hierarchy through graph encoders.
  arXiv  Detail & Related papers  (2023-05-26T12:41:49Z)
• HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification [18.03202012033514]
  We propose hierarchy-aware Tree Isomorphism Network (HiTIN) to enhance the text representations with only syntactic information of the label hierarchy. We conduct experiments on three commonly used datasets and the results demonstrate that HiTIN could achieve better test performance and less memory consumption.
  arXiv  Detail & Related papers  (2023-05-24T14:14:08Z)
• An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text [20.100081284294973]
  We compare four methods for multi-label classification, two based on an encoder only, and two based on an encoder-decoder. Our results show that encoder-decoder methods outperform encoder-only methods, with a growing advantage on more complex datasets.
  arXiv  Detail & Related papers  (2023-05-09T17:13:53Z)
• Improving Code Search with Hard Negative Sampling Based on Fine-tuning [15.341959871682981]
  We introduce a cross-encoder architecture for code search that jointly encodes the concatenation of query and code. We also introduce a Retriever-Ranker (RR) framework that cascades the dual-encoder and cross-encoder to promote the efficiency of evaluation and online serving.
  arXiv  Detail & Related papers  (2023-05-08T07:04:28Z)
• ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference [70.36083572306839]
  This paper proposes a new training and inference paradigm for re-ranking. We finetune a pretrained encoder-decoder model using in the form of document to query generation. We show that this encoder-decoder architecture can be decomposed into a decoder-only language model during inference.
  arXiv  Detail & Related papers  (2022-04-25T06:26:29Z)
• Label Semantics for Few Shot Named Entity Recognition [68.01364012546402]
  We study the problem of few shot learning for named entity recognition. We leverage the semantic information in the names of the labels as a way of giving the model additional signal and enriched priors. Our model learns to match the representations of named entities computed by the first encoder with label representations computed by the second encoder.
  arXiv  Detail & Related papers  (2022-03-16T23:21:05Z)
• Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations [22.40667024030858]
  Bi-encoders produce fixed-dimensional sentence representations and are computationally efficient. Cross-encoders can leverage their attention heads to exploit inter-sentence interactions for better performance. Trans-Encoder combines the two learning paradigms into an iterative joint framework to simultaneously learn enhanced bi- and cross-encoders.
  arXiv  Detail & Related papers  (2021-09-27T14:06:47Z)
• Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers [149.78470371525754]
  We treat semantic segmentation as a sequence-to-sequence prediction task. Specifically, we deploy a pure transformer to encode an image as a sequence of patches. With the global context modeled in every layer of the transformer, this encoder can be combined with a simple decoder to provide a powerful segmentation model, termed SEgmentation TRansformer (SETR) SETR achieves new state of the art on ADE20K (50.28% mIoU), Pascal Context (55.83% mIoU) and competitive results on Cityscapes.
  arXiv  Detail & Related papers  (2020-12-31T18:55:57Z)
• LabelEnc: A New Intermediate Supervision Method for Object Detection [78.74368141062797]
  We propose a new intermediate supervision method, named LabelEnc, to boost the training of object detection systems. The key idea is to introduce a novel label encoding function, mapping the ground-truth labels into latent embedding. Experiments show our method improves a variety of detection systems by around 2% on COCO dataset.
  arXiv  Detail & Related papers  (2020-07-07T08:55:05Z)
• Rethinking and Improving Natural Language Generation with Layer-Wise Multi-View Decoding [59.48857453699463]
  In sequence-to-sequence learning, the decoder relies on the attention mechanism to efficiently extract information from the encoder. Recent work has proposed to use representations from different encoder layers for diversified levels of information. We propose layer-wise multi-view decoding, where for each decoder layer, together with the representations from the last encoder layer, which serve as a global view, those from other encoder layers are supplemented for a stereoscopic view of the source sequences.
  arXiv  Detail & Related papers  (2020-05-16T20:00:39Z)

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.