相关论文: Representation Learning for Short Text Clustering

Audio captioning aims at using natural language to describe the content of an audio clip. Existing audio captioning systems are generally based on an encoder-decoder architecture, in which acoustic information is extracted by an audio…

Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase,…

Unsupervised representation learning with contrastive learning achieved great success. This line of methods duplicate each training batch to construct contrastive pairs, making each training batch and its augmented version forwarded…

Contrastive representation learning has proven to be an effective self-supervised learning method. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as positives that should be…

Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level…

Machine learning methods have recently achieved high-performance in biomedical text analysis. However, a major bottleneck in the widespread application of these methods is obtaining the required large amounts of annotated training data,…

Automatic text classification (TC) research can be used for real-world problems such as the classification of in-patient discharge summaries and medical text reports, which is beneficial to make medical documents more understandable to…

We present a novel masked image modeling (MIM) approach, context autoencoder (CAE), for self-supervised representation pretraining. We pretrain an encoder by making predictions in the encoded representation space. The pretraining tasks…

In this paper, we propose a novel, effective and simpler end-to-end image clustering auto-encoder algorithm: ICAE. The algorithm uses PEDCC (Predefined Evenly-Distributed Class Centroids) as the clustering centers, which ensures the…

Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the…

Unsupervised and self-supervised representation learning has become popular in recent years for learning useful features from unlabelled data. Representation learning has been mostly developed in the neural network literature, and other…

Despite significant advances in clustering methods in recent years, the outcome of clustering of a natural image dataset is still unsatisfactory due to two important drawbacks. Firstly, clustering of images needs a good feature…

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional…

In order to learn universal sentence representations, previous methods focus on complex recurrent neural networks or supervised learning. In this paper, we propose a mean-max attention autoencoder (mean-max AAE) within the encoder-decoder…

We present Consistent Assignment of Views over Random Partitions (CARP), a self-supervised clustering method for representation learning of visual features. CARP learns prototypes in an end-to-end online fashion using gradient descent…

Deep auto-encoders (DAEs) have achieved great success in learning data representations via the powerful representability of neural networks. But most DAEs only focus on the most dominant structures which are able to reconstruct the data…

In recent years, pre-trained models have become dominant in most natural language processing (NLP) tasks. However, in the area of Automated Essay Scoring (AES), pre-trained models such as BERT have not been properly used to outperform other…

Pre-trained language model representations have been successful in a wide range of language understanding tasks. In this paper, we examine different strategies to integrate pre-trained representations into sequence to sequence models and…

Analyzing and visualizing scientific ensemble datasets with high dimensionality and complexity poses significant challenges. Dimensionality reduction techniques and autoencoders are powerful tools for extracting features, but they often…

This paper presents a new sequence-to-sequence (seq2seq) pre-training method PoDA (Pre-training of Denoising Autoencoders), which learns representations suitable for text generation tasks. Unlike encoder-only (e.g., BERT) or decoder-only…