paper-with-me

홈 › Papers

Order-free Learning Alleviating Exposure Bias in Multi-label Classification

2019-09-08 · Che-Ping Tsai, Hung-Yi Lee

Multi-label classification (MLC) assigns multiple labels to each sample. Prior studies show that MLC can be transformed to a sequence prediction problem with a recurrent neural network (RNN) decoder to model the label dependency. However, training a RNN decoder requires a predefined order of labels, which is not directly available in the MLC specification. Besides, RNN thus trained tends to overfit the label combinations in the training set and have difficulty generating unseen label sequences. In this paper, we propose a new framework for MLC which does not rely on a predefined label order and thus alleviates exposure bias. The experimental results on three multi-label classification benchmark datasets show that our method outperforms competitive baselines by a large margin. We also find the proposed approach has a higher probability of generating label combinations not seen during training than the baseline models. The result shows that the proposed approach has better generalization capability.

📄 PDF Abstract BibTeX arXiv:1909.03434

Code (1)

jackyyy0228/Order-free-Learning-Alleviating-Exposure-Bias-in-Multi-label-Classification pytorch

Tasks

DecoderGeneral ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

Similar Papers 제목 키워드 기반

Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps

2023-05-24 · Mingxiao Li, Tingyu Qu, Ruicong Yao, Wei Sun 외

Diffusion Probabilistic Models (DPM) have shown remarkable efficacy in the synthesis of high-quality images. However, their inference process characteristically requires numerous, potentially hundreds, of iterative steps…

Denoising

Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One

2022-06-26 · Yezhen Wang, Tong Che, Bo Li, Kaitao Song 외

Autoregressive generative models are commonly used, especially for those tasks involving sequential data. They have, however, been plagued by a slew of inherent flaws due to the intrinsic characteristics of chain-style c…

Image GenerationLanguage ModelingLanguage ModellingMachine Translation

Alleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive Summarization

2023-05-03 · ACL 2023 5 · Jiawen Xie, Qi Su, Shaoting Zhang, and Xiaofan Zhang

Most Transformer based abstractive summarization systems have a severe mismatch between training and inference, i.e., exposure bias. From diverse perspectives, we introduce a simple multi-level contrastive learning frame…

Abstractive Text SummarizationContrastive LearningDecoderFew-Shot Learning

Alleviating Exposure Bias via Contrastive Learning for Abstractive Text Summarization

2021-08-26 · Shichao Sun, Wenjie Li

Encoder-decoder models have achieved remarkable success in abstractive text summarization, which aims to compress one or more documents into a shorter version without the loss of the essential content. Unfortunately, the…

Abstractive Text SummarizationContrastive LearningDecoderText Summarization

Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction

2020-09-16 · Findings of the Association for Computational Linguistics 2020 · Ranran Haoran Zhang, Qianying Liu, Aysa Xuemo Fan, Heng Ji 외

Joint entity and relation extraction aims to extract relation triplets from plain text directly. Prior work leverages Sequence-to-Sequence (Seq2Seq) models for triplet sequence generation. However, Seq2Seq enforces an un…

Joint Entity and Relation ExtractionRelationRelation ExtractionTriplet