Related papers: Variational Deep Semantic Hashing for Text Documen…
As deep neural networks become more adept at traditional tasks, many of the most exciting new challenges concern multimodality---observations that combine diverse types, such as image and text. In this paper, we introduce a family of…
Manually labelling large collections of text data is a time-consuming, expensive, and laborious task, but one that is necessary to support machine learning based on text datasets. Active learning has been shown to be an effective way to…
A generative model is developed for deep (multi-layered) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding efficient bottom-up (pretraining) and top-down (refinement)…
Keyphrase provides highly-condensed information that can be effectively used for understanding, organizing and retrieving text content. Though previous studies have provided many workable solutions for automated keyphrase extraction, they…
We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their component sentences. Specifically, we consider scenarios in which annotators explicitly mark sentences (or…
We propose a novel generative model to explore both local and global context for joint learning topics and topic-specific word embeddings. In particular, we assume that global latent topics are shared across documents, a word is generated…
Semantic hashing is an emerging technique for large-scale similarity search based on representing high-dimensional data using similarity-preserving binary codes used for efficient indexing and search. It has recently been shown that…
Past work on story generation has demonstrated the usefulness of conditioning on a generation plan to generate coherent stories. However, these approaches have used heuristics or off-the-shelf models to first tag training stories with the…
Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. However, most prevailing methods trained generative and…
In recent years, deep hashing methods have been proved to be efficient since it employs convolutional neural network to learn features and hashing codes simultaneously. However, these methods are mostly supervised. In real-world…
Semantic word embeddings represent the meaning of a word via a vector, and are created by diverse methods. Many use nonlinear operations on co-occurrence statistics, and have hand-tuned hyperparameters and reweighting methods. This paper…
Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular…
With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time…
How data is represented and operationalized is critical for building computational solutions that are both effective and efficient. A common approach is to represent data objects as binary vectors, denoted \textit{hash codes}, which require…
Supervised hashing aims to map the original features to compact binary codes that are able to preserve label based similarity in the Hamming space. Non-linear hash functions have demonstrated the advantage over linear ones due to their…
Code-switching, the interleaving of two or more languages within a sentence or discourse is pervasive in multilingual societies. Accurate language models for code-switched text are critical for NLP tasks. State-of-the-art data-intensive…
The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far has been framed in a standard supervised way and consists…
Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…
Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…
Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing…