Related papers: Unsupervised Text Style Transfer using Language Mo…

As the application space of language models continues to evolve, a natural question to ask is how we can quickly adapt models to new tasks. We approach this classic question from a continual learning perspective, in which we aim to continue…

We study cross-lingual sequence tagging with little or no labeled data in the target language. Adversarial training has previously been shown to be effective for training cross-lingual sentence classifiers. However, it is not clear if…

We present an alternative perspective on the training of generative adversarial networks (GANs), showing that the training step for a GAN generator decomposes into two implicit subproblems. In the first, the discriminator provides new…

One of the main motivations for training high quality image generative models is their potential use as tools for image manipulation. Recently, generative adversarial networks (GANs) have been able to generate images of remarkable quality.…

In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with…

In the development of neural text-to-speech systems, model pre-training with a large amount of non-target speakers' data is a common approach. However, in terms of ultimately achieved system performance for target speaker(s), the actual…

Target-oriented sentiment classification aims at classifying sentiment polarities over individual opinion targets in a sentence. RNN with attention seems a good fit for the characteristics of this task, and indeed it achieves the…

Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems should be paraphrases of their inputs. However,…

Cross-domain natural language generation (NLG) is still a difficult task within spoken dialogue modelling. Given a semantic representation provided by the dialogue manager, the language generator should generate sentences that convey…

In this paper, we propose a generative knowledge transfer technique that trains an RNN based language model (student network) using text and output probabilities generated from a previously trained RNN (teacher network). The text generation…

Autoregressive models based on Transformers have become the prevailing approach for generating music compositions that exhibit comprehensive musical structure. These models are typically trained by minimizing the negative log-likelihood…

In this paper, we propose an efficient transfer leaning methods for training a personalized language model using a recurrent neural network with long short-term memory architecture. With our proposed fast transfer learning schemes, a…

Today text classification models have been widely used. However, these classifiers are found to be easily fooled by adversarial examples. Fortunately, standard attacking methods generate adversarial texts in a pair-wise way, that is, an…

The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification, a rationale, for their predictions. We approach…

Generative Adversarial Networks (GANs) are a promising approach for text generation that, unlike traditional language models (LM), does not suffer from the problem of ``exposure bias''. However, A major hurdle for understanding the…

Generative Adversarial Networks (GANs) for text generation have recently received many criticisms, as they perform worse than their MLE counterparts. We suspect previous text GANs' inferior performance is due to the lack of a reliable…

We study the problem of unsupervised domain adaptation, which aims to adapt classifiers trained on a labeled source domain to an unlabeled target domain. Many existing approaches first learn domain-invariant features and then construct…

Generative models defining joint distributions over parse trees and sentences are useful for parsing and language modeling, but impose restrictions on the scope of features and are often outperformed by discriminative models. We propose a…

Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning is applied to voice conversion successfully based on speaker labels. However, the performance of model…

Moving from limited-domain natural language generation (NLG) to open domain is difficult because the number of semantic input combinations grows exponentially with the number of domains. Therefore, it is important to leverage existing…