Related papers: Data Augmentation for Spoken Language Understandin…

End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employing the standard pipeline composed of a separately trained…

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…

Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including…

Sequential data often possesses a hierarchical structure with complex dependencies between subsequences, such as found between the utterances in a dialogue. In an effort to model this kind of generative process, we propose a neural…

Generative language modelling has surged in popularity with the emergence of services such as ChatGPT and Google Gemini. While these models have demonstrated transformative potential in productivity and communication, they overwhelmingly…

Spoken Language Understanding (SLU) is composed of two subtasks: intent detection (ID) and slot filling (SF). There are two lines of research on SLU. One jointly tackles these two subtasks to improve their prediction accuracy, and the other…

The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and…

Powerful generative models, particularly in Natural Language Modelling, are commonly trained by maximizing a variational lower bound on the data log likelihood. These models often suffer from poor use of their latent variable, with ad-hoc…

In recent years, pretrained neural language models (PNLMs) have taken the field of natural language processing by storm, achieving new benchmarks and state-of-the-art performances. These models often rely heavily on annotated data, which…

Current approaches to phrase break prediction address crucial prosodic aspects of text-to-speech systems but heavily rely on vast human annotations from audio or text, incurring significant manual effort and cost. Inherent variability in…

Data augmentation methods for Natural Language Processing tasks are explored in recent years, however they are limited and it is hard to capture the diversity on sentence level. Besides, it is not always possible to perform data…

Recent deep learning models have shown improving results to natural language generation (NLG) irrespective of providing sufficient annotated data. However, a modest training data may harm such models performance. Thus, how to build a…

In modular dialogue systems, natural language understanding (NLU) and natural language generation (NLG) are two critical components, where NLU extracts the semantics from the given texts and NLG is to construct corresponding natural…

Structuring the latent space in probabilistic deep generative models, e.g., variational autoencoders (VAEs), is important to yield more expressive models and interpretable representations, and to avoid overfitting. One way to achieve this…

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…

Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation. Previous work…

Spoken Language Models (SLMs) have emerged as a promising paradigm for speech synthesis by bypassing explicit grapheme-to-phoneme pipelines. However, their effectiveness in low-resource languages remains fundamentally limited by the…

End-to-end architectures have been recently proposed for spoken language understanding (SLU) and semantic parsing. Based on a large amount of data, those models learn jointly acoustic and linguistic-sequential features. Such architectures…

For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often only very few text…

How to model distribution of sequential data, including but not limited to speech and human motions, is an important ongoing research problem. It has been demonstrated that model capacity can be significantly enhanced by introducing…