Stuart E. Middleton
YOU?
Author Swipe
View article: Data rescue of historical tables through semi-supervised table structure recognition
Data rescue of historical tables through semi-supervised table structure recognition Open
This study uses a novel semi-supervised learning framework to explore Tabular Structure Recognition (TSR) for digitizing historical documents, specifically employing the CascadeTabNet model. TSR is crucial for transforming archival tabular…
View article: Data Rescue of Historical Tables Through Semi-Supervised Table Structure Recognition
Data Rescue of Historical Tables Through Semi-Supervised Table Structure Recognition Open
This study uses a novel semi-supervised learning framework to explore Tabular Structure Recognition (TSR) for digitizing historical documents, specifically employing the CascadeTabNet model. TSR is crucial for transforming archival tabular…
View article: Tabular context-aware optical character recognition and tabular data reconstruction for historical records
Tabular context-aware optical character recognition and tabular data reconstruction for historical records Open
Digitizing historical tabular records is essential for preserving and analyzing valuable data across various fields, but it presents challenges due to complex layouts, mixed text types, and degraded document quality. This paper introduces …
View article: CPIQA: Climate Paper Image Question Answering Dataset for Retrieval-Augmented Generation with Context-based Query Expansion
CPIQA: Climate Paper Image Question Answering Dataset for Retrieval-Augmented Generation with Context-based Query Expansion Open
Misinformation about climate science is a serious challenge for our society. This paper introduces CPIQA (Climate Paper Image Question-Answering), a new question-answer dataset featuring 4,551 full-text open-source academic papers in the a…
View article: Adversarial Defense without <i>Adversarial Defense</i> : Enhancing Language Model Robustness via Instance-level Principal Component Removal
Adversarial Defense without <i>Adversarial Defense</i> : Enhancing Language Model Robustness via Instance-level Principal Component Removal Open
Pre-trained language models (PLMs) have driven substantial progress in natural language processing but remain vulnerable to adversarial attacks, raising concerns about their robustness in real-world applications. Previous studies have soug…
View article: Tabular Context-aware Optical Character Recognition and Tabular Data Reconstruction for Historical Records
Tabular Context-aware Optical Character Recognition and Tabular Data Reconstruction for Historical Records Open
Digitizing historical tabular records is essential for preserving and analyzing valuable data across various fields, but it presents challenges due to complex layouts, mixed text types, and degraded document quality. This paper introduces …
View article: AI for Defence: Readiness, Resilience and Mental Health
AI for Defence: Readiness, Resilience and Mental Health Open
Artificial Intelligence (AI) is a cross-cutting technology that is making a major impact on behavioural analysis in both the defence and mental health domains. Employing AI well could boost readiness and resilience of military personnel. T…
View article: Implementing responsible innovation: the role of the meso-level(s) between project and organisation
Implementing responsible innovation: the role of the meso-level(s) between project and organisation Open
Much of academic discussion of responsible innovation (RI) has focused on RI integration into research projects. In addition, significant attention has also been paid to RI structures and policies at the research policy and institutional l…
View article: Data Rescue for Historical Document Tables Using Semi-Supervised Learning
Data Rescue for Historical Document Tables Using Semi-Supervised Learning Open
This study uses a novel semi-supervised learning framework to explore Tabular Structure Recognition (TSR) for digitizing historical documents, specifically employing the CascadeTabNet model. TSR is crucial for transforming archival tabular…
View article: Sharenting and social media properties: Exploring vicarious data harms and sociotechnical mitigations
Sharenting and social media properties: Exploring vicarious data harms and sociotechnical mitigations Open
In this paper, we demonstrate how social media technologies can co-produce data-related harms unless preventative measures are instituted. To this end, we draw on a passive ethnography of a public Facebook group in the UK practicing sharen…
View article: Do prompt positions really matter?
Do prompt positions really matter? Open
Prompt-based models have gathered a lot of attention from researchers due to their remarkable advancements in the fields of zero-shot and few-shot learning. Developing an effective prompt template plays a critical role. However, prior stud…
View article: rafamestre/Multimodal-USElecDeb60To16: v1.0.0
rafamestre/Multimodal-USElecDeb60To16: v1.0.0 Open
Dataset and codes for the Multimodal USElecDeb60To16 dataset, released in the paper "Augmenting pre-trained language models with audio feature embedding for argumentation mining in political debates", published at the Findings of the 17th …
View article: rafamestre/Multimodal-USElecDeb60To16: v1.0.0
rafamestre/Multimodal-USElecDeb60To16: v1.0.0 Open
Dataset and codes for the Multimodal USElecDeb60To16 dataset, released in the paper "Augmenting pre-trained language models with audio feature embedding for argumentation mining in political debates", published at the Findings of the 17th …
View article: rafamestre/Multimodal-USElecDeb60To16: v1.0.0
rafamestre/Multimodal-USElecDeb60To16: v1.0.0 Open
Dataset and codes for the Multimodal USElecDeb60To16 dataset, released in the paper "Augmenting pre-trained language models with audio feature embedding for argumentation mining in political debates", published at the Findings of the 17th …
View article: Augmenting pre-trained language models with audio feature embedding for argumentation mining in political debates
Augmenting pre-trained language models with audio feature embedding for argumentation mining in political debates Open
The integration of multimodality in natural language processing (NLP) tasks seeks to exploit the complementary information contained in two or more modalities, such as text, audio and video. This paper investigates the integration of often…
View article: Social media text mining and network analysis for decision support in natural crisis management
Social media text mining and network analysis for decision support in natural crisis management Open
A core issue in crisis management is to extract from the mass of incoming information what is important for situational awareness during mass emergencies. Based on a case study we develop a prototypical application, TweetComp1, which is in…
View article: IDN-Sum
IDN-Sum Open
Summarizing Interactive Digital Narratives (IDN) presents some unique challenges to existing text summarization models especially around capturing interactive elements in addition to important plot points. In this paper we describe the fir…
View article: IDN-Sum
IDN-Sum Open
Summarizing Interactive Digital Narratives (IDN) presents some unique challenges to existing text summarization models especially around capturing interactive elements in addition to important plot points. In this paper we describe the fir…
View article: Trust, regulation, and human-in-the-loop AI
Trust, regulation, and human-in-the-loop AI Open
Artificial intelligence (AI) systems employ learning algorithms which adapt to their users and environment, with learning either pre-trained or allowed to adapt during deployment. Because AI can optimize its behaviour, a unit's factory mod…
View article: Detecting Moments of Change and Suicidal Risks in Longitudinal User Texts Using Multi-task Learning
Detecting Moments of Change and Suicidal Risks in Longitudinal User Texts Using Multi-task Learning Open
This work describes the classification system proposed for the Computational Linguistics and Clinical Psychology (CLPsych) Shared Task 2022. We propose the use of multitask learning approach with bidirectional long-short term memory (Bi-LS…
View article: M-Arg: Multimodal Multimodal Argument Mining Dataset
M-Arg: Multimodal Multimodal Argument Mining Dataset Open
No description provided.
View article: M-Arg: Multimodal Multimodal Argument Mining Dataset
M-Arg: Multimodal Multimodal Argument Mining Dataset Open
No description provided.
View article: A Response to Draft Online Safety Bill - a call for evidence from the Joint Committee
A Response to Draft Online Safety Bill - a call for evidence from the Joint Committee Open
This report is the Trustworthy Autonomous Hub (TAS-hub) response to the call for evidence from the Joint Committee on the Draft Online Safety Bill. The Joint Committee was established to consider the Government's draft Bill to establish a …
View article: stuartemiddleton/glosat_table_dataset: v1.0.0
stuartemiddleton/glosat_table_dataset: v1.0.0 Open
HIP-2021 paper release. Datasets and model checkpoints can can be found on zenodo
View article: GloSAT Historical Measurement Table Dataset
GloSAT Historical Measurement Table Dataset Open
Dataset containing scanned historical measurement table documents from ship logs and land measurement stations. Annotations provided in this dataset are designed to allow finergrained table detection and table structure recognition models …
View article: GloSAT Historical Measurement Table Dataset
GloSAT Historical Measurement Table Dataset Open
Dataset containing scanned historical measurement table documents from ship logs and land measurement stations. Annotations provided in this dataset are designed to allow finergrained table detection and table structure recognition models …
View article: Combining Machine Learning and Human Experts to Predict Match Outcomes in Football: A Baseline Model
Combining Machine Learning and Human Experts to Predict Match Outcomes in Football: A Baseline Model Open
In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so w…