相关论文: KATE: K-Competitive Autoencoder for Text

Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images. However, for downstream tasks like semantic classification, the representations learned by VAE are less competitive than…

Deep learning has witnessed significant advancements in recent years at the cost of increasing training, inference, and model storage overhead. While existing model compression methods strive to reduce the number of model parameters while…

Principal component analysis, dictionary learning, and auto-encoders are all unsupervised methods for learning representations from a large amount of training data. In all these methods, the higher the dimensions of the input data, the…

Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc search but incurs the vocabulary mismatch problem. Although…

We present a variation of the Autoencoder (AE) that explicitly maximizes the mutual information between the input data and the hidden representation. The proposed model, the InfoMax Autoencoder (IMAE), by construction is able to learn a…

Recently, generative adversarial networks and adversarial autoencoders have gained a lot of attention in machine learning community due to their exceptional performance in tasks such as digit classification and face recognition. They map…

Learning the latent representation of data in unsupervised fashion is a very interesting process that provides relevant features for enhancing the performance of a classifier. For speech emotion recognition tasks, generating effective…

In this work we explore deep generative models of text in which the latent representation of a document is itself drawn from a discrete language model distribution. We formulate a variational auto-encoder for inference in this model and…

Object-centric representations form the basis of human perception, and enable us to reason about the world and to systematically generalize to new settings. Currently, most works on unsupervised object discovery focus on slot-based…

Most generative document models act on bag-of-words input in an attempt to focus on the semantic content and thereby partially forego syntactic information. We argue that it is preferable to keep the original word order intact and…

Textual graphs are ubiquitous in real-world applications, featuring rich text information with complex relationships, which enables advanced research across various fields. Textual graph representation learning aims to generate…

Task specific fine-tuning of a pre-trained neural language model using a custom softmax output layer is the de facto approach of late when dealing with document classification problems. This technique is not adequate when labeled examples…

Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats…

Pre-trained language representation models, such as BERT, capture a general language representation from large-scale corpora, but lack domain-specific knowledge. When reading a domain text, experts make inferences with relevant knowledge.…

Pretrained deep-learning models are the go-to solution for images or text. However, for tabular data the standard is still to train tree-based models. Indeed, transfer learning on tables hits the challenge of data integration: finding…

Syntactic information contains structures and rules about how text sentences are arranged. Incorporating syntax into text modeling methods can potentially benefit both representation learning and generation. Variational autoencoders (VAEs)…

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…

Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that pre-trained…

We address two challenges in topic models: (1) Context information around words helps in determining their actual meaning, e.g., "networks" used in the contexts "artificial neural networks" vs. "biological neuron networks". Generative topic…

Learning to fuse vision and language information and representing them is an important research problem with many applications. Recent progresses have leveraged the ideas of pre-training (from language modeling) and attention layers in…