Related papers: Formal Semantic Control over Language Models
Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While this has been well investigated in Computer Vision, in…
Achieving precise semantic control over the latent spaces of Variational AutoEncoders (VAEs) holds significant value for downstream tasks in NLP as the underlying generative mechanisms could be better localised, explained and improved upon.…
Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, compositionality, and generalisation capabilities of Transformer-based auto-regressive language…
Deep generative neural networks, such as Variational AutoEncoders (VAEs), offer an opportunity to better understand and control language models from the perspective of sentence-level latent spaces. To combine the controllability of VAE…
While mel-spectrograms have been widely utilized as intermediate representations in zero-shot text-to-speech (TTS), their inherent redundancy leads to inefficiency in learning text-speech alignment. Compact VAE-based latent representations…
Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…
Formal/symbolic semantics can provide canonical, rigid controllability and interpretability to sentence representations due to their \textit{localisation} or \textit{composition} property. How can we deliver such property to the current…
The field of Text-to-Speech has experienced huge improvements last years benefiting from deep learning techniques. Producing realistic speech becomes possible now. As a consequence, the research on the control of the expressiveness,…
Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…
The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To…
Effective AI governance requires structured approaches for stakeholders to access and verify AI system behavior. With the rise of large language models, Natural Language Explanations (NLEs) are now key to articulating model behavior, which…
An ability to model a generative process and learn a latent representation for speech in an unsupervised fashion will be crucial to process vast quantities of unlabelled speech data. Recently, deep probabilistic generative models such as…
The mathematical representation of semantics is a key issue for Natural Language Processing (NLP). A lot of research has been devoted to finding ways of representing the semantics of individual words in vector spaces. Distributional…
Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation…
Pretrained language models are long known to be subpar in capturing sentence and document-level semantics. Though heavily investigated, transferring perturbation-based methods from unsupervised visual representation learning to NLP remains…
Do state-of-the-art models for language understanding already have, or can they easily learn, abilities such as boolean coordination, quantification, conditionals, comparatives, and monotonicity reasoning (i.e., reasoning about word…
We present evidence that language models (LMs) of code can learn to represent the formal semantics of programs, despite being trained only to perform next-token prediction. Specifically, we train a Transformer model on a synthetic corpus of…
In this paper, we introduce the Variational Autoencoder (VAE) to an end-to-end speech synthesis model, to learn the latent representation of speaking styles in an unsupervised manner. The style representation learned through VAE shows good…
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…
Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…