Engineering Commons^™

Bevers: A General, Simple, And Performant Framework For Automatic Fact Verification, Mitchell Dehaven

Department of Computer Science and Engineering: Dissertations, Theses, and Student Research

Fact verification has become an important process, primarily done manually by humans, to verify the authenticity of claims and statements made online. Increasingly, social media companies have utilized human effort to debunk false claims on their platforms, opting to either tag the content as misleading or false, or removing it entirely to combat misinformation on their sites. In tandem, the field of automatic fact verification has become a subject of focus among the natural language processing (NLP) community, spawning new datasets and research. The most popular dataset is the Fact Extraction and VERification (FEVER) dataset. In this thesis an end-to-end …

Attention In The Faithful Self-Explanatory Nlp Models, Mostafa Rafaiejokandan

Department of Computer Science and Engineering: Dissertations, Theses, and Student Research

Deep neural networks (DNNs) can perform impressively in many natural language processing (NLP) tasks, but their black-box nature makes them inherently challenging to explain or interpret. Self-Explanatory models are a new approach to overcoming this challenge, generating explanations in human-readable languages besides task objectives like answering questions. The main focus of this thesis is the explainability of NLP tasks, as well as how attention methods can help enhance performance. Three different attention modules are proposed, SimpleAttention, CrossSelfAttention, and CrossModality. It also includes a new dataset transformation method called Two-Documents that converts every dataset into two separate documents required by the …

Training Thinner And Deeper Neural Networks: Jumpstart Regularization, Carles Riera, Camilo Rey, Thiago Serra, Eloi Puertas, Oriol Pujol

Faculty Conference Papers and Presentations

Neural networks are more expressive when they have multiple layers. In turn, conventional training methods are only successful if the depth does not lead to numerical issues such as exploding or vanishing gradients, which occur less frequently when the layers are sufficiently wide. However, increasing width to attain greater depth entails the use of heavier computational resources and leads to overparameterized models. These subsequent issues have been partially addressed by model compression methods such as quantization and pruning, some of which relying on normalization-based regularization of the loss function to make the effect of most parameters negligible. In this work, …

A Machine Learning Framework For Identifying Molecular Biomarkers From Transcriptomic Cancer Data, Md Abdullah Al Mamun

FIU Electronic Theses and Dissertations

Cancer is a complex molecular process due to abnormal changes in the genome, such as mutation and copy number variation, and epigenetic aberrations such as dysregulations of long non-coding RNA (lncRNA). These abnormal changes are reflected in transcriptome by turning oncogenes on and tumor suppressor genes off, which are considered cancer biomarkers.

However, transcriptomic data is high dimensional, and finding the best subset of genes (features) related to causing cancer is computationally challenging and expensive. Thus, developing a feature selection framework to discover molecular biomarkers for cancer is critical.

Traditional approaches for biomarker discovery calculate the fold change for each …