Search Results for author: Mark Stevenson

Found 51 papers, 14 papers with code

Stopping Methods for Technology Assisted Reviews based on Point Processes

1 code implementation14 Nov 2023 Mark Stevenson, Reem Bin-Hezam

Technology Assisted Review (TAR), which aims to reduce the effort required to screen collections of documents for relevance, is used to develop systematic reviews of medical evidence and identify documents that must be disclosed in response to legal proceedings.

Point Processes

Scalable Label-efficient Footpath Network Generation Using Remote Sensing Data and Self-supervised Learning

1 code implementation18 Sep 2023 Xinye Wanyan, Sachith Seneviratne, Kerry Nice, Jason Thompson, Marcus White, Nano Langenheim, Mark Stevenson

The annotation of segmentation tasks, especially labeling remote sensing images with specialized requirements, is very expensive, so we aim to introduce a pipeline requiring less labeled data.

Representation Learning Self-Supervised Learning

On the Security Vulnerabilities of Text-to-SQL Models

no code implementations28 Nov 2022 Xutan Peng, YiPeng Zhang, Jingfeng Yang, Mark Stevenson

Although it has been demonstrated that Natural Language Processing (NLP) algorithms are vulnerable to deliberate attacks, the question of whether such weaknesses can lead to software security threats is under-explored.


UserReg: A Simple but Strong Model for Rating Prediction

no code implementations15 Feb 2021 Haiyang Zhang, Ivan Ganchev, Nikola S. Nikolov, Mark Stevenson

We compare the effectiveness of UserReg with three linear CF models that are widely-used as baselines, and with a set of recently proposed complex models that are based on deep learning or graph techniques.

Collaborative Filtering Recommendation Systems

Identifying safe intersection design through unsupervised feature extraction from satellite imagery

no code implementations29 Oct 2020 Jasper S. Wijnands, Haifeng Zhao, Kerry A. Nice, Jason Thompson, Katherine Scully, Jingqiu Guo, Mark Stevenson

The World Health Organization has listed the design of safer intersections as a key intervention to reduce global road trauma.

Identifying Automatically Generated Headlines using Transformers

no code implementations NAACL (NLP4IF) 2021 Antonis Maronikolakis, Hinrich Schutze, Mark Stevenson

False information spread via the internet and social media influences public opinion and user activity, while generative models enable fake content to be generated faster and more cheaply than had previously been possible.


Automatic Generation of Topic Labels

1 code implementation29 May 2020 Areej Alokaili, Nikolaos Aletras, Mark Stevenson

A topic is usually represented by a list of terms ranked by their probability but, since these can be difficult to interpret, various approaches have been developed to assign descriptive labels to topics.

Descriptive Information Retrieval +3

Understanding Linearity of Cross-Lingual Word Embedding Mappings

1 code implementation2 Apr 2020 Xutan Peng, Mark Stevenson, Chenghua Lin, Chen Li

The technique of Cross-Lingual Word Embedding (CLWE) plays a fundamental role in tackling Natural Language Processing challenges for low-resource languages.

Representation Learning Word Embeddings

Real-time monitoring of driver drowsiness on mobile platforms using 3D neural networks

no code implementations15 Oct 2019 Jasper S. Wijnands, Jason Thompson, Kerry A. Nice, Gideon D. P. A. Aschwanden, Mark Stevenson

Phone applications reduce the need for specialised hardware and hence, enable a cost-effective roll-out of the technology across the driving population.

Action Recognition Optical Flow Estimation

The 'Paris-end' of town? Urban typology through machine learning

no code implementations8 Oct 2019 Kerry A. Nice, Jason Thompson, Jasper S. Wijnands, Gideon D. P. A. Aschwanden, Mark Stevenson

A (novel) neural network-based framework is trained with imagery from the largest 1692 cities in the world and the resulting models are used to compare within-city locations from Melbourne and Sydney to determine the closest connections between these areas and their international comparators.

BIG-bench Machine Learning

Modelling Stopping Criteria for Search Results using Poisson Processes

1 code implementation IJCNLP 2019 Alison Sneyd, Mark Stevenson

Text retrieval systems often return large sets of documents, particularly when applied to large collections.

Retrieval Text Retrieval

Streetscape augmentation using generative adversarial networks: insights related to health and wellbeing

no code implementations14 May 2019 Jasper S. Wijnands, Kerry A. Nice, Jason Thompson, Haifeng Zhao, Mark Stevenson

Deep learning using neural networks has provided advances in image style transfer, merging the content of one image (e. g., a photo) with the style of another (e. g., a painting).

Style Transfer

Re-Ranking Words to Improve Interpretability of Automatically Generated Topics

1 code implementation WS 2019 Areej Alokaili, Nikolaos Aletras, Mark Stevenson

Making their output interpretable is an important area of research with applications to areas such as the enhancement of exploratory search interfaces and the development of interpretable machine learning models.

Interpretable Machine Learning Re-Ranking +1

Topic or Style? Exploring the Most Useful Features for Authorship Attribution

1 code implementation COLING 2018 Yunita Sari, Mark Stevenson, Andreas Vlachos

Approaches to authorship attribution, the task of identifying the author of a document, are based on analysis of individuals{'} writing style and/or preferred topics.

Text Categorization

HiDE: a Tool for Unrestricted Literature Based Discovery

no code implementations COLING 2018 Judita Preiss, Mark Stevenson

We introduce HiDE (Hidden Discovery Explorer), an online knowledge browsing tool which allows fast access to hidden knowledge generated from all abstracts in Medline.

Improving distant supervision using inference learning

no code implementations IJCNLP 2015 Roland Roller, Eneko Agirre, Aitor Soroa, Mark Stevenson

Distant supervision is a widely applied approach to automatic training of relation extraction systems and has the advantage that it can generate large amounts of labelled data with minimal effort.

Relation Extraction

Mapping WordNet synsets to Wikipedia articles

no code implementations LREC 2012 Fern, Samuel o, Mark Stevenson

Lexical knowledge bases (LKBs), such as WordNet, have been shown to be useful for a range of language processing tasks.

Information Retrieval Word Sense Disambiguation

Matching Cultural Heritage items to Wikipedia

no code implementations LREC 2012 Eneko Agirre, Ander Barrena, Oier Lopez de Lacalle, Aitor Soroa, Fern, Samuel o, Mark Stevenson

Digitised Cultural Heritage (CH) items usually have short descriptions and lack rich contextual information.

Entity Linking

Cannot find the paper you are looking for? You can Submit a new open access paper.