Related papers: Modular Grammatical Evolution for the Generation o…
A significantly under-explored area of evolutionary optimization in the literature is the study of optimization methodologies that can evolve along with the problems solved. Particularly, present evolutionary optimization approaches…
he greatest weakness of evolutionary algorithms, widely used today, is the premature convergence due to the loss of population diversity over generations. To overcome this problem, several algorithms have been proposed, such as the…
Grammatical error correction (GEC) aims to correct grammatical, spelling, and semantic errors in natural language text. With the growing of large language models (LLMs), direct text generation has gradually become the focus of the GEC…
When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…
Training Generative Adversarial Networks (GANs) is notoriously challenging. We propose and study an architectural modification, self-modulation, which improves GAN performance across different data sets, architectures, losses, regularizers,…
How to automatically design better machine learning programs is an open problem within AutoML. While evolution has been a popular tool to search for better ML programs, using learning itself to guide the search has been less successful and…
The standard paradigm of neural language generation adopts maximum likelihood estimation (MLE) as the optimizing method. From a distributional view, MLE in fact minimizes the Kullback-Leibler divergence (KLD) between the distribution of the…
Recent works in Grammatical Error Correction (GEC) have leveraged the progress in Neural Machine Translation (NMT), to learn rewrites from parallel corpora of grammatically incorrect and corrected sentences, achieving state-of-the-art…
Generative Adversarial Networks (GAN) is an adversarial model, and it has been demonstrated to be effective for various generative tasks. However, GAN and its variants also suffer from many training problems, such as mode collapse and…
Self-supervised neural language models have recently found wide applications in generative design of organic molecules and protein sequences as well as representation learning for downstream structure classification and functional…
Graphs are increasingly becoming ubiquitous as models for structured data. A generative model that closely mimics the structural properties of a given set of graphs has utility in a variety of domains. Much of the existing work require that…
Model-Based Engineering (MBE) has streamlined software development by focusing on abstraction and automation. The adoption of MBE in Maintenance and Evolution (MBM&E), however, is still limited due to poor tool support and a lack of…
Many experiments have been performed that use evolutionary algorithms for learning the topology and connection weights of a neural network that controls a robot or virtual agent. These experiments are not only performed to better understand…
Modular Neural Networks (MNNs) demonstrate various advantages over monolithic models. Existing MNNs are generally $\textit{explicit}$: their modular architectures are pre-defined, with individual modules expected to implement distinct…
Recurrent neural networks have achieved remarkable success at generating sequences with complex structures, thanks to advances that include richer embeddings of input and cures for vanishing gradients. Trained only on sequences from a known…
It is still a challenging task to learn a neural text generation model under the framework of generative adversarial networks (GANs) since the entire training process is not differentiable. The existing training strategies either suffer…
As real-world knowledge is constantly evolving, ensuring the timeliness and accuracy of a model's knowledge is crucial. This has made knowledge editing in large language models increasingly important. However, existing knowledge editing…
Large Language Models (LLMs) have achieved remarkable results. However, existing models are expensive to train and deploy, and it is also difficult to expand their knowledge beyond pre-training data without forgetting previous knowledge.…
Locally Linear Embedding (LLE) is a nonlinear spectral dimensionality reduction and manifold learning method. It has two main steps which are linear reconstruction and linear embedding of points in the input space and embedding space,…
We perform neural machine translation of sentence fragments in order to create large amounts of training data for English grammatical error correction. Our method aims at simulating mistakes made by second language learners, and produces a…