Search Results for author:
Found 31 papers, 17 papers with code
Generating Textual Explanations for Machine Learning Models Performance: A Table-to-Text Task
This paper proposes a new natural language generation (NLG) task where neural models are trained to generate textual explanations, analytically describing the classification performance of ML models based on the metrics’ scores reported in the tables.
RAR-b: Reasoning as Retrieval Benchmark
Under the emerging Retrieval-augmented Generation (RAG) paradigm, we envision the need to evaluate next-level language understanding abilities of embedding models, and take a conscious look at the reasoning abilities stored in them.
Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics
Achieving an effective fine-grained appearance variation over 2D facial images, whilst preserving facial identity, is a challenging task due to the high complexity and entanglement of common 2D facial feature encoding spaces.
Textual Localization: Decomposing Multi-concept Images for Subject-Driven Text-to-Image Generation
Subject-driven text-to-image diffusion models empower users to tailor the model to new concepts absent in the pre-training dataset using a few sample images.
Pixel Sentence Representation Learning
To our knowledge, this is the first representation learning method devoid of traditional language models for understanding sentence and document semantics, marking a stride closer to human-like textual comprehension.
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval
We further annotate the image-text pairs with two-level subset-subcategory hierarchy annotations to facilitate a more comprehensive evaluation of the baselines.
Length is a Curse and a Blessing for Document-level Semantics
In recent years, contrastive learning (CL) has been extensively utilized to recover sentence and document-level encoding capability from pre-trained language models.
Audio Contrastive based Fine-tuning
Audio classification plays a crucial role in speech and sound processing tasks with a wide range of applications.
Racial Bias within Face Recognition: A Survey
Facial recognition is one of the most academically studied and industrially developed areas within computer vision where we readily find associated applications deployed globally.
Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation
To leverage information from text pairs, we additionally introduce a novel supervised model we call dual directional learning (DDL), which is designed to integrate with our proposed VSAR model.
On Isotropy, Contextualization and Learning Dynamics of Contrastive-based Sentence Representation Learning
In this paper, we aim to help guide future designs of sentence representation learning methods by taking a closer look at contrastive SRL through the lens of isotropy, contextualization and learning dynamics.
Knowing the Past to Predict the Future: Reinforcement Virtual Learning
Reinforcement Learning (RL)-based control system has received considerable attention in recent decades.
INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations
XAI with natural language processing aims to produce human-readable explanations as evidence for AI decision-making, which addresses explainability and transparency.
Decision Making
Explainable Artificial Intelligence (XAI)
+2
Does lossy image compression affect racial bias within face recognition?
Yes - This study investigates the impact of commonplace lossy image compression on face recognition algorithms with regard to the racial characteristics of the subject.
Towards Graph Representation Learning Based Surgical Workflow Anticipation
Hence, we propose a graph representation learning framework to comprehensively represent instrument motions in the surgical workflow anticipation problem.
Using Orientation to Distinguish Overlapping Chromosomes
Instead, we separate the chromosome instances in a second stage, predicting the orientation of the chromosomes by the model and use it as one of the key distinguishing factors of the chromosomes.
MuLD: The Multitask Long Document Benchmark
The impressive progress in NLP techniques has been driven by the development of multi-task benchmarks such as GLUE and SuperGLUE.
Ranked #1 on
Translation
on MuLD (OpenSubtitles)
Ask me in your own words: paraphrasing for multitask question answering
Multitask learning has led to significant advances in Natural Language Processing, including the decaNLP benchmark where question answering is used to frame 10 natural language understanding tasks in a single model.
Measuring Hidden Bias within Face Recognition via Racial Phenotypes
We use the set of observable characteristics of an individual face where a race-related facial phenotype is hence specific to the human face and correlated to the racial profile of the subject.
ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference
We introduce a new model for NLI called External Knowledge Enhanced BERT (ExBERT), to enrich the contextual representation with real-world commonsense knowledge from external knowledge sources and enhance BERT's language understanding and reasoning capabilities.
Towards Equal Gender Representation in the Annotations of Toxic Language Detection
We then apply the learned associations between gender and language to toxic language classifiers, finding that models trained exclusively on female-annotated data perform 1. 8% better than those trained solely on male-annotated data and that training models on data after removing all offensive words reduces bias in the model by 55. 5% while increasing the sensitivity by 0. 4%.
Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanations
Deep Learning of neural networks has progressively become more prominent in healthcare with models reaching, or even surpassing, expert accuracy levels.
Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learning
On the MIMIC-III and Henan-Renmin EHR datasets, we report a detection accuracy of 77% against the Longitudinal Adversarial Attack.
Curvature-based Feature Selection with Application in Classifying Electronic Health Records
Disruptive technologies provides unparalleled opportunities to contribute to the identifications of many aspects in pervasive healthcare, from the adoption of the Internet of Things through to Machine Learning (ML) techniques.
On Modality Bias in the TVQA Dataset
Our results demonstrate that models trained on only the visual information can answer ~45% of the questions, while using only the subtitles achieves ~68%.
Trying Bilinear Pooling in Video-QA
We share our results on the TVQA baseline model, and the recently proposed heterogeneous-memory-enchanced multimodal attention (HME) model.
Bilinear Fusion of Commonsense Knowledge with Attention-Based NLI Models
BiCAM incorporates real-world commonsense knowledge into NLI models.
Simulating Brain Signals: Creating Synthetic EEG Data via Neural-Based Generative Models for Improved SSVEP Classification
Despite significant recent progress in the area of Brain-Computer Interface (BCI), there are numerous shortcomings associated with collecting Electroencephalography (EEG) signals in real-world environments.
Quantitative Methods Signal Processing
An Exploration of Dropout with RNNs for Natural Language Inference
In this paper, we propose a novel RNN model for NLI and empirically evaluate the effect of applying dropout at different layers in the model.
Using Machine Learning to reduce the energy wasted in Volunteer Computing Environments
We demonstrate, through the use of simulation, how we can reduce this wasted energy by targeting tasks at computers less likely to be needed for primary use, predicting this idle time through machine learning.
SMS Spam Filtering using Probabilistic Topic Modelling and Stacked Denoising Autoencoder
In This paper we present a novel approach to spam filtering and demonstrate its applicability with respect to SMS messages.
