S2vNTM: Semi-supervised vMF Neural Topic Modeling
Not on the map. Why?
Abstract (arXiv)
Language model based methods are powerful techniques for text classification. However, the models have several shortcomings. (1) It is difficult to integrate human knowledge such as keywords. (2) It needs a lot of resources to train the models. (3) It relied on large text data to pretrain. In this paper, we propose Semi-Supervised vMF Neural Topic Modeling (S2vNTM) to overcome these difficulties. S2vNTM takes a few seed keywords as input for topics. S2vNTM leverages the pattern of keywords to identify potential topics, as well as optimize the quality of topics' keywords sets. Across a variety of datasets, S2vNTM outperforms existing semi-supervised topic modeling methods in classification accuracy with limited keywords provided. S2vNTM is at least twice as fast as baselines.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 64 references that are in the map. First posted on arXiv 6 Jul 2023.
Builds on
28 of 64 references.
References · 28
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
- 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
- 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
- 2019How to Fine-Tune BERT for Text Classification?cited by 409
- 2019Topic Modeling in Embedding Spacescited by 224
- 2018Hyperspherical Variational Auto-Encoderscited by 188
- 2020Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherencecited by 121
- 2015Neural Variational Inference for Text Processingcited by 111
16 more
- 2017Generating Sentences by Editing Prototypescited by 88
- 2020Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approachcited by 83
- 2017Discovering Discrete Latent Topics with Neural Variational Inferencecited by 79
- 2018Spherical Latent Spaces for Stable Variational Autoencoderscited by 66
- 2020Neural Topic Model via Optimal Transportcited by 50
- 2019Spherical Text Embeddingcited by 49
- 2020X-Class: Text Classification with Extremely Weak Supervisioncited by 45
- 2018Weakly-Supervised Hierarchical Text Classificationcited by 42
- 2020ERNIE-Doc: A Retrospective Long-Document Modeling Transformercited by 31
- 2019Discriminative Topic Mining via Category-Name Guided Text Embeddingcited by 29
- 2016Anchored Correlation Explanation: Topic Modeling with Minimal Domain Knowledgecited by 23
- 2022Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentationcited by 22
- 2016Hard Negative Mining for Metric Learning Based Zero-Shot Classificationcited by 18
- 2023vONTSS: vMF based semi-supervised neural topic modeling with optimal transportcited by 16
- 2021Keyword Assisted Embedded Topic Modelcited by 9
- 2023KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillationcited by 3
Built on by
Citing papers per year: 2024: 1.
1 paper.