One Objective for All Models --- Self-supervised Learning for Topic Models
Self-supervised learning has significantly improved the performance of many NLP tasks. In this paper, we highlight a key advantage of self-supervised learning - when applied to data generated by topic models, self-supervised learning can be oblivious to the specific model, and hence is less susceptible to model mis-specification. In particular, we prove that commonly used self-supervised objectives based on reconstruction or contrastive samples can both recover useful posterior information for general topic models. Empirically, we show that the same objectives can perform competitively against posterior inference using the correct model, while outperforming posterior inference using mis-specified model.
Code (0)
등록된 구현이 없습니다.
Tasks
AllSelf-Supervised LearningTopic ModelsSimilar Papers 제목 키워드 기반
Understanding The Robustness of Self-supervised Learning Through Topic Modeling
Self-supervised learning has significantly improved the performance of many NLP tasks. However, how can self-supervised learning discover useful representations, and why is it better than traditional approaches such as p…
Self-Supervised LearningTopic ModelsPrototypical Contrastive Predictive Coding
Transferring representational knowledge of a model to another is a wide-ranging topic in machine learning. Those applications include the distillation of a large supervised or self-supervised teacher model to a smaller s…
Contrastive LearningKnowledge DistillationModel CompressionSelf-Supervised LearningSame Author or Just Same Topic? Towards Topic-Independent Style Representations
Style is an integral component of language. Recent advances in the development of style representations have increasingly used training objectives from authorship verification (AV): Do two texts have the same author? The…
Authorship VerificationSimilarity Analysis of Self-Supervised Speech Representations
Self-supervised speech representation learning has recently been a prosperous research topic. Many algorithms have been proposed for learning useful representations from large-scale unlabeled data, and their applications…
Representation LearningSpeech Representation LearningOnline Iterative Self-Alignment for Radiology Report Generation
Radiology Report Generation (RRG) is an important research topic for relieving radiologist' heavy workload. Existing RRG models mainly rely on supervised fine-tuning (SFT) based on different model architectures using dat…
Reinforcement Learning (RL)