Related papers: Dual Latent Variable Model for Low-Resource Natura…
This paper investigates the challenges and potential solutions for improving machine learning systems for low-resource languages. State-of-the-art models in natural language processing (NLP), text-to-speech (TTS), speech-to-text (STT), and…
Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference. In this paper, we demonstrate that n-gram LM can be…
Recently generating natural language explanations has shown very promising results in not only offering interpretable explanations but also providing additional information and supervision for prediction. However, existing approaches…
It has been previously observed that training Variational Recurrent Autoencoders (VRAE) for text generation suffers from serious uninformative latent variables problem. The model would collapse into a plain language model that totally…
Recently, parallel text generation has received widespread attention due to its success in generation efficiency. Although many advanced techniques are proposed to improve its generation quality, they still need the help of an…
Conditional variational models, using either continuous or discrete latent variables, are powerful for open-domain dialogue response generation. However, previous works show that continuous latent variables tend to reduce the coherence of…
One of the biggest challenges of end-to-end language generation from meaning representations in dialogue systems is making the outputs more natural and varied. Here we take a large corpus of 50K crowd-sourced utterances in the restaurant…
Variational Autoencoders are powerful models for unsupervised learning. However deep models with several layers of dependent stochastic variables are difficult to train which limits the improvements obtained using these highly expressive…
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…
Neural dialogue models, despite their successes, still suffer from lack of relevance, diversity, and in many cases coherence in their generated responses. These issues can attributed to reasons including (1) short-range model architectures…
Neural network based approaches to data-to-text natural language generation (NLG) have gained popularity in recent years, with the goal of generating a natural language prompt that accurately realizes an input meaning representation. To…
Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…
Non-parametric models, such as Gaussian Processes (GP), show promising results in the analysis of complex data. Their applications in neuroscience data have recently gained traction. In this research, we introduce a novel neural decoder…
This paper explores deep latent variable models for semi-supervised paraphrase generation, where the missing target pair for unlabelled data is modelled as a latent paraphrase sequence. We present a novel unsupervised model named…
Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models. In this work, to generate high quality synthetic data for low-resource tagging tasks, we…
Learning to generate fluent natural language from structured data with neural networks has become an common approach for NLG. This problem can be challenging when the form of the structured data varies between examples. This paper presents…
Natural Language Inference Generation task is to generate a text hypothesis given a text premise and a logical relation between the two. This task can be used in data augmentation and controllable text generation in practice. In this paper,…
Dialogue data in real scenarios tend to be sparsely available, rendering data-starved end-to-end dialogue systems trained inadequately. We discover that data utilization efficiency in low-resource scenarios can be enhanced by mining…
We re-examine the situation entity (SE) classification task with varying amounts of available training data. We exploit a Transformer-based variational autoencoder to encode sentences into a lower dimensional latent space, which is used to…
Large Language Models (LLMs) achieve strong performance across diverse tasks, but their effectiveness often depends on the quality of the provided context. Retrieval-Augmented Generation (RAG) enriches prompts with external information, but…