Related papers: Neural Topic Modeling with Bidirectional Adversari…

Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works (Benz et al., 2020; Xu et al., 2021; Tian…

Topic modeling analyzes documents to learn meaningful patterns of words. For documents collected in sequence, dynamic topic models capture how these patterns vary over time. We develop the dynamic embedded topic model (D-ETM), a generative…

Neural models have recently been used in text summarization including headline generation. The model can be trained using a set of document-headline pairs. However, the model does not explicitly consider topical similarities and differences…

Recent studies suggest that ``memorization'' is one important factor for overparameterized deep neural networks (DNNs) to achieve optimal performance. Specifically, the perfectly fitted DNNs can memorize the labels of many atypical samples,…

The success of neural summarization models stems from the meticulous encodings of source articles. To overcome the impediments of limited and sometimes noisy training data, one promising direction is to make better use of the available…

Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. In this paper, we propose a Retrieval-Enhanced Adversarial Training (REAT) method…

Though word embeddings and topics are complementary representations, several past works have only used pretrained word embeddings in (neural) topic modeling to address data sparsity in short-text or small collection of documents. This work…

Gradient-based adversarial training is widely used in improving the robustness of neural networks, while it cannot be easily adapted to natural language processing tasks since the embedding space is discrete. In natural language processing…

Adversarial training (AT) is a powerful regularization method for neural networks, aiming to achieve robustness to input perturbations. Yet, the specific effects of the robustness obtained from AT are still unclear in the context of natural…

We present a new algorithm to learn a deep neural network model robust against adversarial attacks. Previous algorithms demonstrate an adversarially trained Bayesian Neural Network (BNN) provides improved robustness. We recognize the…

In this paper, we study a new learning paradigm for Neural Machine Translation (NMT). Instead of maximizing the likelihood of the human translation as in previous works, we minimize the distinction between human translation and the…

Marrying topic models and language models exposes language understanding to a broader source of document-level context beyond sentences via topics. While introducing topical semantics in language models, existing approaches incorporate…

Topic modelling has been a successful technique for text analysis for almost twenty years. When topic modelling met deep neural networks, there emerged a new and increasingly popular research area, neural topic models, with over a hundred…

Automated analysis of clinical notes is attracting increasing attention. However, there has not been much work on medical term abbreviation disambiguation. Such abbreviations are abundant, and highly ambiguous, in clinical documents. One of…

Unsupervised domain adaptation aims to transfer rich knowledge from the annotated source domain to the unlabeled target domain with the same label space. One prevalent solution is the bi-discriminator domain adversarial network, which…

Dialogue related Machine Reading Comprehension requires language models to effectively decouple and model multi-turn dialogue passages. As a dialogue development goes after the intentions of participants, its topic may not keep constant…

Topic models have been successfully used for analyzing text documents. However, with existing topic models, many documents are required for training. In this paper, we propose a neural network-based few-shot learning method that can learn a…

Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive…

Both visual and auditory information are valuable to determine the salient regions in videos. Deep convolution neural networks (CNN) showcase strong capacity in coping with the audio-visual saliency prediction task. Due to various factors…

Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by clinicians, for instance, containing holes or disconnected…