Related papers: Learning from Multiple Sources for Data-to-Text an…

Recent thrilling progress in large-scale text-to-image (T2I) models has unlocked unprecedented synthesis quality of AI-generated content (AIGC) including image generation, 3D and video composition. Further, personalized techniques enable…

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…

Heterogeneous Text-Attributed Graphs (HTAGs), where different types of entities are not only associated with texts but also connected by diverse relationships, have gained widespread popularity and application across various domains.…

A real-world text corpus sometimes comprises not only text documents but also semantic links between them (e.g., academic papers in a bibliographic network are linked by citations and co-authorships). Text documents and semantic connections…

Learning to learn (L2L) trains a meta-learner to assist the learning of a task-specific base learner. Previously, it was shown that a meta-learner could learn the direct rules to update learner parameters; and that the learnt neural…

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

Multi-source translation is an approach to exploit multiple inputs (e.g. in two different languages) to increase translation accuracy. In this paper, we examine approaches for multi-source neural machine translation (NMT) using an…

We study the problem of generating inferential texts of events for a variety of commonsense like \textit{if-else} relations. Existing approaches typically use limited evidence from training examples and learn for each relation individually.…

For each goal-oriented dialog task of interest, large amounts of data need to be collected for end-to-end learning of a neural dialog system. Collecting that data is a costly and time-consuming process. Instead, we show that we can use only…

Autonomous agents are able to draw on a wide variety of potential sources of task knowledge; however current approaches invariably focus on only one or two. Here we investigate the challenges and impact of exploiting diverse knowledge…

Creating high-quality annotated data for task-oriented dialog (ToD) is known to be notoriously difficult, and the challenges are amplified when the goal is to create equitable, culturally adapted, and large-scale ToD datasets for multiple…

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information…

Deep learning yields great results across many fields, from speech recognition, image classification, to translation. But for each problem, getting a deep model to work well involves research into the architecture and a long period of…

Large-scale pretrained language models have achieved outstanding performance on natural language understanding tasks. However, it is still under investigating how to apply them to dialogue generation tasks, especially those with responses…

Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labeled data can be difficult to obtain in many applications. Existing approaches…

Large Text-to-Image(T2I) diffusion models have shown a remarkable capability to produce photorealistic and diverse images based on text inputs. However, existing works only support limited language input, e.g., English, Chinese, and…

We tackle the task of automatically discriminating between human and machine translations. As opposed to most previous work, we perform experiments in a multilingual setting, considering multiple languages and multilingual pretrained…

Unsupervised text style transfer aims to transfer the underlying style of text but keep its main content unchanged without parallel data. Most existing methods typically follow two steps: first separating the content from the original…

This paper proposes a method for extracting a lightweight subset from a text-to-speech (TTS) corpus ensuring synthetic speech quality. In recent years, methods have been proposed for constructing large-scale TTS corpora by collecting…

Neural language models often fail to generate diverse and informative texts, limiting their applicability in real-world problems. While previous approaches have proposed to address these issues by identifying and penalizing undesirable…