Amir H. Payberah
YOU?
Author Swipe
View article: PBBQ: A Persian Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models
PBBQ: A Persian Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models Open
With the increasing adoption of large language models (LLMs), ensuring their alignment with social norms has become a critical concern. While prior research has examined bias detection in various languages, there remains a significant gap …
View article: Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM
Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM Open
Similar to text-based Large Language Models (LLMs), Speech-LLMs exhibit emergent abilities and context awareness. However, whether these similarities extend to gender bias remains an open question. This study proposes a methodology leverag…
View article: AquaCluster: Using Satellite Images And Self-supervised Machine Learning Networks To Detect Water Hidden Under Vegetation
AquaCluster: Using Satellite Images And Self-supervised Machine Learning Networks To Detect Water Hidden Under Vegetation Open
In recent years, the wide availability of high-resolution radar satellite images has enabled the remote monitoring of wetland surface areas. Machine learning models have achieved state-of-the-art results in segmenting wetlands from satelli…
View article: Utilizing Large Language Models for Ablation Studies in Machine Learning and Deep Learning
Utilizing Large Language Models for Ablation Studies in Machine Learning and Deep Learning Open
In Machine Learning (ML) and Deep Learning (DL) research, ablation studies are typically performed to provide insights into the individual contribution of different building blocks and components of an ML/DL system (e.g., a deep neural net…
View article: Deep Neural Network Weight Initialization from Hyperparameter Tuning Trials
Deep Neural Network Weight Initialization from Hyperparameter Tuning Trials Open
View article: SCORE: Skill-Conditioned Online Reinforcement Learning
SCORE: Skill-Conditioned Online Reinforcement Learning Open
Solving complex long-horizon tasks through Reinforcement Learning (RL) from scratch presents challenges related to efficient exploration. Two common approaches to reduce complexity and enhance exploration efficiency are (i) integrating lea…
View article: FogFLeeT: Fog-Level Federated Transfer Learning for Adaptive Transport Mode Detection
FogFLeeT: Fog-Level Federated Transfer Learning for Adaptive Transport Mode Detection Open
Transport Mode Detection (TMD) systems play a pivotal role in facilitating applications in transport, urban planning, and more. Exploiting the advancements in smartphone sensing capabilities, TMD systems have evolved for mobile application…
View article: Wiki-based Prompts for Enhancing Relation Extraction using Language Models
Wiki-based Prompts for Enhancing Relation Extraction using Language Models Open
Prompt-tuning and instruction-tuning of language models have exhibited significant results in few-shot Natural Language Processing (NLP) tasks, such as Relation Extraction (RE), which involves identifying relationships between entities wit…
View article: یادداشت مترجم
یادداشت مترجم Open
View article: Translator's Note
Translator's Note Open
View article: DeepAqua: Semantic segmentation of wetland water surfaces with SAR imagery using deep neural networks without manually annotated data
DeepAqua: Semantic segmentation of wetland water surfaces with SAR imagery using deep neural networks without manually annotated data Open
Deep learning and remote sensing techniques have significantly advanced water surface monitoring; however, the need for annotated data remains a challenge. This is particularly problematic in wetland detection, where water extent varies ov…
View article: ContrastNER: Contrastive-based Prompt Tuning for Few-shot NER
ContrastNER: Contrastive-based Prompt Tuning for Few-shot NER Open
Prompt-based language models have produced encouraging results in numerous applications, including Named Entity Recognition (NER) tasks. NER aims to identify entities in a sentence and provide their types. However, the strong performance o…
View article: DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge Distillation
DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge Distillation Open
Deep learning and remote sensing techniques have significantly advanced water monitoring abilities; however, the need for annotated data remains a challenge. This is particularly problematic in wetland detection, where water extent varies …
View article: Scalable Artificial Intelligence for Earth Observation Data Using Hopsworks
Scalable Artificial Intelligence for Earth Observation Data Using Hopsworks Open
This paper introduces the Hopsworks platform to the entire Earth Observation (EO) data community and the Copernicus programme. Hopsworks is a scalable data-intensive open-source Artificial Intelligence (AI) platform that was jointly develo…
View article: Accelerate Model Parallel Training by Using Efficient Graph Traversal Order in Device Placement
Accelerate Model Parallel Training by Using Efficient Graph Traversal Order in Device Placement Open
Modern neural networks require long training to reach decent performance on massive datasets. One common approach to speed up training is model parallelization, where large neural networks are split across multiple devices. However, differ…
View article: Accelerate Model Parallel Deep Learning Training Using Effective Graph Traversal Order in Device Placement
Accelerate Model Parallel Deep Learning Training Using Effective Graph Traversal Order in Device Placement Open
View article: A Survey of Big Data Pipeline Orchestration Tools from the Perspective of the DataCloud Pro ject
A Survey of Big Data Pipeline Orchestration Tools from the Perspective of the DataCloud Pro ject Open
This paper presents a survey of existing tools for Big Data pipeline orchestration based on a comparative framework developed in the DataCloud project. We propose criteria for evaluating the tools to support reusability, flexible pipeline …
View article: Big Data Workflows: Locality-Aware Orchestration Using Software Containers
Big Data Workflows: Locality-Aware Orchestration Using Software Containers Open
The emergence of the edge computing paradigm has shifted data processing from centralised infrastructures to heterogeneous and geographically distributed infrastructures. Therefore, data processing solutions must consider data locality to …
View article: Conceptualization and scalable execution of big data workflows using domain-specific languages and software containers
Conceptualization and scalable execution of big data workflows using domain-specific languages and software containers Open
Big Data processing, especially with the increasing proliferation of Internet of Things (IoT) technologies and convergence of IoT, edge and cloud computing technologies, involves handling massive and complex data sets on heterogeneous reso…
View article: Siamese Neural Networks for Detecting Complementary Products
Siamese Neural Networks for Detecting Complementary Products Open
Marina Angelovska, Sina Sheikholeslami, Bas Dunn, Amir H. Payberah. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop. 2021.
View article: Predicting the risk of emergency admission with machine learning: Development and validation using linked electronic health records
Predicting the risk of emergency admission with machine learning: Development and validation using linked electronic health records Open
The use of machine learning and addition of temporal information led to substantially improved discrimination and calibration for predicting the risk of emergency admission. Model performance remained stable across a range of prediction ti…
View article: An adaptive algorithm for anomaly and novelty detection in evolving data streams
An adaptive algorithm for anomaly and novelty detection in evolving data streams Open
In the era of big data, considerable research focus is being put on designing efficient algorithms capable of learning and extracting high-level knowledge from ubiquitous data streams in an online fashion. While, most existing algorithms a…
View article: DOIT WP3 report on predictive modeling and data insights : Version 5.0
DOIT WP3 report on predictive modeling and data insights : Version 5.0 Open
View article: Boosting Vertex-Cut Partitioning for Streaming Graphs
Boosting Vertex-Cut Partitioning for Streaming Graphs Open
While the algorithms for streaming graph partitioning are proved promising, they fall short of creating timely partitions when applied on large graphs. For example, it takes 415 seconds for a state-of-the-art partitioner to work on a socia…
View article: A Distributed Algorithm for Large-Scale Graph Partitioning
A Distributed Algorithm for Large-Scale Graph Partitioning Open
Balanced graph partitioning is an NP-complete problem with a wide range of applications. These applications include many large-scale distributed problems, including the optimal storage of large sets of graph-structured data over several ho…