Related papers: Pretraining the Noisy Channel Model for Task-Orien…

Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…

Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling. However, most VAE conversation models match the approximate posterior distribution over the latent variables to a simple prior such as standard…

Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models. While current models offer impressive…

In this work, we study how the finetuning stage in the pretrain-finetune framework changes the behavior of a pretrained neural language generator. We focus on the transformer encoder-decoder model for the open-domain dialogue response…

We consider a real-time communication system with noisy feedback consisting of a Markov source, a forward and a backward discrete memoryless channels, and a receiver with finite memory. The objective is to design an optimal communication…

Pre-trained language models have established the state-of-the-art on various natural language processing tasks, including dialogue summarization, which allows the reader to quickly access key information from long conversations in meetings,…

In this work, we study dialogue scenarios that start from chit-chat but eventually switch to task-related services, and investigate how a unified dialogue model, which can engage in both chit-chat and task-oriented dialogues, takes the…

In decentralized active noise control (ANC) systems, crosstalk between multichannel secondary sources and error microphones significantly degrades control accuracy. Moreover, prefiltering reference signals in filtered-x (Fx) type algorithms…

Dialogue response selection aims to select an appropriate response from several candidates based on a given user and system utterance history. Most existing works primarily focus on post-training and fine-tuning tailored for cross-encoders.…

In this thesis, we leverage the neural copy mechanism and memory-augmented neural networks (MANNs) to address existing challenge of neural task-oriented dialogue learning. We show the effectiveness of our strategy by achieving good…

During the pre-training step of natural language models, the main objective is to learn a general representation of the pre-training dataset, usually requiring large amounts of textual data to capture the complexity and diversity of natural…

Natural language generation plays a critical role in spoken dialogue systems. We present a new approach to natural language generation for task-oriented dialogue using recurrent neural networks in an encoder-decoder framework. In contrast…

Training task-oriented dialogue systems typically requires turn-level annotations for interacting with their APIs: e.g. a dialogue state and the system actions taken at each step. These annotations can be costly to produce, error-prone, and…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

When generating text from probabilistic models, the chosen decoding strategy has a profound effect on the resulting text. Yet the properties elicited by various decoding strategies do not always transfer across natural language generation…

Bayesian deep learning approaches assume model parameters to be latent random variables and infer posterior distributions to quantify uncertainty, increase safety and trust, and prevent overconfident and unpredictable behavior. However,…

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarchical syntactic features - as opposed to incorrect linear…

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…

We propose the first method to adaptively modify the duration of a given speech signal. Our approach uses a Bayesian framework to define a latent attention map that links frames of the input and target utterances. We train a masked…

Multi-task learning of dense prediction tasks, by sharing both the encoder and decoder, as opposed to sharing only the encoder, provides an attractive front to increase both accuracy and computational efficiency. When the tasks are similar,…