S. Y. Mensah
YOU?
Author Swipe
View article: WHERE DO WE KEEP THE GODS? GALAMSEY, SACRED ECOLOGY AND THE CRISIS OF SUSTAINABILITY IN GHANA
WHERE DO WE KEEP THE GODS? GALAMSEY, SACRED ECOLOGY AND THE CRISIS OF SUSTAINABILITY IN GHANA Open
n Ghana, where rivers are revered as abodes of deities, illegal gold mining (galamsey) is not just an environmental crisis –it is a spiritual catastrophe. This study interrogates the paradox of galamsey’s economic appeal versus its desecra…
View article: Deep Learning-Based Speech Enhancement for Robust Sound Classification in Security Systems
Deep Learning-Based Speech Enhancement for Robust Sound Classification in Security Systems Open
Deep learning has emerged as a powerful technique for speech enhancement, particularly in security systems where audio signals are often degraded by non-stationary noise. Traditional signal processing methods struggle in such conditions, m…
View article: A Variational Approach for Mitigating Entity Bias in Relation Extraction
A Variational Approach for Mitigating Entity Bias in Relation Extraction Open
Mitigating entity bias is a critical challenge in Relation Extraction (RE), where models often rely excessively on entities, resulting in poor generalization. This paper presents a novel approach to address this issue by adapting a Variati…
View article: Sustainability in Agricultural Value Chains: Evidence from the Pineapple Sector in Ghana
Sustainability in Agricultural Value Chains: Evidence from the Pineapple Sector in Ghana Open
The pineapple sector in Ghana plays an important role in the country’s economy, providing a livelihood for actors along the value chain. This study aims to understand the factors influencing the sustainability of the major actors along the…
View article: Chondrocytes Embedded in Agarose Generate Distinct Metabolic Heat Profiles Based on Media Carbon Sources
Chondrocytes Embedded in Agarose Generate Distinct Metabolic Heat Profiles Based on Media Carbon Sources Open
Human chondrocytes are responsible for cartilage repair and homeostasis through metabolic production of precursors to collagen and other matrix components. This metabolism is sensitive both to the availability of media energy sources as we…
View article: FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking
FinNLI: Novel Dataset for Multi-Genre Financial Natural Language Inference Benchmarking Open
We introduce FinNLI, a benchmark dataset for Financial Natural Language Inference (FinNLI) across diverse financial texts like SEC Filings, Annual Reports, and Earnings Call transcripts. Our dataset framework ensures diverse premise-hypoth…
View article: Deep Learning-Based Speech Enhancement for Robust Sound Classification in Security Systems
Deep Learning-Based Speech Enhancement for Robust Sound Classification in Security Systems Open
Deep learning has become an effective technique in speech enhancement that has enhanced the classification of sound in security systems. Traditional approaches are ineffective in noisy conditions, so detecting important sound events like g…
View article: VERO: Verification and Zero-Shot Feedback Acquisition for Few-Shot Multimodal Aspect-Level Sentiment Classification
VERO: Verification and Zero-Shot Feedback Acquisition for Few-Shot Multimodal Aspect-Level Sentiment Classification Open
Deep learning approaches for multimodal aspect-level sentiment classification (MALSC) often require extensive data, which is costly and time-consuming to obtain. To mitigate this, current methods typically fine-tune small-scale pretrained …
View article: Tunable High-Frequency Acoustoelectric Current Oscillations in Fluorine-Doped Single-Walled Carbon Nanotubes
Tunable High-Frequency Acoustoelectric Current Oscillations in Fluorine-Doped Single-Walled Carbon Nanotubes Open
Herein, we report on a fluorine-doped single-walled carbon nanotube (FSWCNT) phenomenon, that yields tunable high-frequency self-sustained acoustoelectric direct current (ADC) oscillations. A tractable analytical method was used in the hyp…
View article: Investigation of Acoustomagnetoelectric Effect in Bandgap Graphene by the Boltzmann Transport Equation
Investigation of Acoustomagnetoelectric Effect in Bandgap Graphene by the Boltzmann Transport Equation Open
We study the acoustomagnetoelectric (AME) effect in two-dimensional graphene with an energy bandgap using the semiclassical Boltzmann transport equation within the hypersound regime, (where represents the acoustic wavenumber and is the mea…
View article: Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement
Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement Open
State-of-the-art target-oriented opinion word extraction (TOWE) models typically use BERT-based text encoders that operate on the word level, along with graph convolutional networks (GCNs) that incorporate syntactic information extracted f…
View article: Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction
Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction Open
Opinion target extraction (OTE) or aspect extraction (AE) is a fundamental task in opinion mining that aims to extract the targets (or aspects) on which opinions have been expressed. Recent work focus on cross-domain OTE, which is typicall…
View article: Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement
Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement Open
State-of-the-art target-oriented opinion word extraction (TOWE) models typically use BERT-based text encoders that operate on the word level, along with graph convolutional networks (GCNs) that incorporate syntactic information extracted f…
View article: Thermal conductivity in fluorine-doped single-walled carbon nanotubes
Thermal conductivity in fluorine-doped single-walled carbon nanotubes Open
Herein, we report on the axial thermal conductivity (κzz) of a non-degenerate fluorine-doped single-walled carbon nanotubes (FSWCNTs) under single and dual relaxation models. We derived the expressions for the carrier thermal current densi…
View article: Social capital and knowledge creation: a higher education institution networks
Social capital and knowledge creation: a higher education institution networks Open
Social capital concept has become popular over the past decades. What is not known in literature and worth investigating is the network designs and nature that enhance the development of new learning ideas and knowledge creation. The aim o…
View article: Giant thermoelectric figure of merit in fluorine-doped single walled-carbon nanotubes
Giant thermoelectric figure of merit in fluorine-doped single walled-carbon nanotubes Open
Herein, we report on a giant thermoelectric figure of merit (ZT) of a non-degenerate fluorine-doped single-walled carbon nanotube (FSWCNT) using a tractable analytical approach and the phonon lattice Boltzmann model (LBM). We investigate t…
View article: A Hierarchical N-Gram Framework for Zero-Shot Link Prediction
A Hierarchical N-Gram Framework for Zero-Shot Link Prediction Open
Due to the incompleteness of knowledge graphs (KGs), zero-shot link prediction (ZSLP) which aims to predict unobserved relations in KGs has attracted recent interest from researchers. A common solution is to use textual features of relatio…
View article: A Hierarchical N-Gram Framework for Zero-Shot Link Prediction
A Hierarchical N-Gram Framework for Zero-Shot Link Prediction Open
Knowledge graphs typically contain a large number of entities but often cover only a fraction of all relations between them (i.e., incompleteness). Zero-shot link prediction (ZSLP) is a popular way to tackle the problem by automatically id…
View article: Contrastive Learning with Expectation-Maximization for Weakly Supervised Phrase Grounding
Contrastive Learning with Expectation-Maximization for Weakly Supervised Phrase Grounding Open
Weakly supervised phrase grounding aims to learn an alignment between phrases in a caption and objects in a corresponding image using only caption-image annotations, i.e., without phrase-object annotations. Previous methods typically use a…
View article: A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity Linking
A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity Linking Open
Recent interest in entity linking has focused in the zero-shot scenario, where at test time the entity mention to be labelled is never seen during training, or may belong to a different domain from the source domain. Current work leverage …
View article: Herding Behavior of Ghana Stock Market Participants: A Daily Analysis
Herding Behavior of Ghana Stock Market Participants: A Daily Analysis Open
This study investigates the herding behavior of Ghana stock market participants and its impact on stock returns. Using panel data of 38 equities listed on the Ghana stock market, the data spans from 2011 to 2019. Fixed effect model was use…
View article: An Empirical Study on Leveraging Position Embeddings for Target-oriented\n Opinion Words Extraction
An Empirical Study on Leveraging Position Embeddings for Target-oriented\n Opinion Words Extraction Open
Target-oriented opinion words extraction (TOWE) (Fan et al., 2019b) is a new\nsubtask of target-oriented sentiment analysis that aims to extract opinion\nwords for a given aspect in text. Current state-of-the-art methods leverage\nposition…
View article: Giant Thermoelectric Figure of Merit in Fluorine Doped Single Walled Carbon Nanotube
Giant Thermoelectric Figure of Merit in Fluorine Doped Single Walled Carbon Nanotube Open
Herein, we report on a giant thermoelectric figure of merit of a non-degenerate fluorine-doped single-walled carbon nanotube (FSWCNT) using a tractable analytical approach and the phonon lattice Boltzmann model (LBM). We investigate the in…
View article: Acoustoelectric Current in Graphene Nanoribbon due to Landau Damping
Acoustoelectric Current in Graphene Nanoribbon due to Landau Damping Open
We perform self-consistent analysis of the Boltzmann transport equation for momentum and energy in the hypersound regime i.e., ql >> 1 ( q is the acoustic wavenumber and l is the mean free path). Here, we investigate Landau damping of acou…