Paul Nulty
YOU?
Author Swipe
View article: Thinking Fast and Slow in Large Language Models: a Review of the Decision-Making Capabilities of Generative AI Agents
Thinking Fast and Slow in Large Language Models: a Review of the Decision-Making Capabilities of Generative AI Agents Open
Large language models (LLMs) are increasingly being used in a wide range of everyday decision-making scenarios, transforming the way people make choices and interact with technology. However, despite their seemingly ‘superhuman’ capabiliti…
View article: Argument Mining with Graph Representation Learning
Argument Mining with Graph Representation Learning Open
Argument Mining (AM) is a unique task in Natural Language Processing (NLP) that targets arguments: a meaningful logical structure in human language.Since the argument plays a significant role in the legal field, the interdisciplinary study…
View article: quanteda/readtext: CRAN v0.82
quanteda/readtext: CRAN v0.82 Open
readtext v0.82 Moves some quanteda functions to this package: docvars(), docnames(), texts() Updates print method to use pillar instead of tibble Modernizes some of the testthat syntax. readtext v0.81 Fixed a problem in the examples breaki…
View article: Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks
Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks Open
The contextual word embedding model, BERT, has proved its ability on downstream tasks with limited quantities of annotated data. BERT and its variants help to reduce the burden of complex annotation work in many interdisciplinary research …
View article: Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks
Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks Open
The contextual word embedding model, BERT, has proved its ability on downstream tasks with limited quantities of annotated data. BERT and its variants help to reduce the burden of complex annotation work in many interdisciplinary research …
View article: Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks
Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks Open
The contextual word embedding model, BERT, has proved its ability on downstream tasks with limited quantities of annotated data. BERT and its variants help to reduce the burden of complex annotation work in many interdisciplinary research …
View article: Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks
Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks Open
The contextual word embedding model, BERT, has proved its ability on downstream tasks with limited quantities of annotated data. BERT and its variants help to reduce the burden of complex annotation work in many interdisciplinary research …
View article: Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks
Enhancing Legal Argument Mining with Domain Pre-training and Neural Networks Open
The contextual word embedding model, BERT, has proved its ability on downstream tasks with limited quantities of annotated data. BERT and its variants help to reduce the burden of complex annotation work in many interdisciplinary research …
View article: Crisis Domain Adaptation Using Sequence-to-sequence Transformers
Crisis Domain Adaptation Using Sequence-to-sequence Transformers Open
User-generated content (UGC) on social media can act as a key source of information for emergency responders in crisis situations. However, due to the volume concerned, computational techniques are needed to effectively filter and prioriti…
View article: Transformer-based Multi-task Learning for Disaster Tweet Categorisation
Transformer-based Multi-task Learning for Disaster Tweet Categorisation Open
Social media has enabled people to circulate information in a timely fashion, thus motivating people to post messages seeking help during crisis situations. These messages can contribute to the situational awareness of emergency responders…
View article: A Comparative Study on Word Embeddings in Deep Learning for Text Classification
A Comparative Study on Word Embeddings in Deep Learning for Text Classification Open
Word embeddings act as an important component of deep models for providing input features in downstream language tasks, such as sequence labelling and text classification. In the last decade, a substantial number of word embedding methods …
View article: quanteda/quanteda: CRAN v2.0.1
quanteda/quanteda: CRAN v2.0.1 Open
Changes Moved data_corpus_irishbudget2010 and data_corpus_dailnoconf1991 to the quanteda.textmodels package. Em dashes and double dashes between words, whether surrounded by a space or not, are now converted to " - " to distinguish them fr…
View article: The Immigration Issue in the European Electoral Campaign in the UK: Text-Mining Public Debate from Newspapers and Social Media
The Immigration Issue in the European Electoral Campaign in the UK: Text-Mining Public Debate from Newspapers and Social Media Open
In recent years, the issue of immigration has become increasingly salient in the UK political and media debate. Moreover, with the development and persistence of the economic and financial crisis within the EU, immigration has been linked …
View article: The UCD-Net System at SemEval-2020 Task 1: Temporal Referencing with Semantic Network Distances
The UCD-Net System at SemEval-2020 Task 1: Temporal Referencing with Semantic Network Distances Open
This paper describes the UCD system entered for SemEval 2020 Task 1: Unsupervised Lexical Semantic Change Detection. We propose a novel method based on distance between temporally referenced nodes in a semantic network constructed from a c…
View article: The Idea of Liberty, 1600–1800: A Distributional Concept Analysis
The Idea of Liberty, 1600–1800: A Distributional Concept Analysis Open
This article uses computational and statistical methods for analyzing the concept of liberty 1600-1800. Based on a bespoke set of tools for parsing conceptual structures it contributes to the literature on the concept of liberty and engage…
View article: The Conceptual Foundations of the Modern Idea of Government in the British Eighteenth Century: A Distributional Concept Analysis
The Conceptual Foundations of the Modern Idea of Government in the British Eighteenth Century: A Distributional Concept Analysis Open
This essay sets out a new method for the history of ideas. Using a mixed approach combining computer assisted reading methods with more traditional close reading, the essay tracks the evolution of a set of terms over the eighteenth century…
View article: Distributional Concept Analysis
Distributional Concept Analysis Open
This article proposes a novel computational method for discerning the structure and history of concepts. Based on the analysis of co-occurrence data in large data sets, the method creates a measure of “binding” that enables the constructio…
View article: quanteda: An R package for the quantitative analysis of textual data
quanteda: An R package for the quantitative analysis of textual data Open
quanteda is an R package providing a comprehensive workflow and toolkit for natural language processing tasks such as corpus management, tokenization, analysis, and visualization.It has extensive functions for applying dictionary analysis,…
View article: Improving a Fundamental Measure of Lexical Association
Improving a Fundamental Measure of Lexical Association Open
Pointwise mutual information (PMI), a simple measure of lexical association, is part of several algorithms used as models of lexical semantic memory. Typically, it is used as a component of more complex distributional models rather than in…
View article: Semantic Network Analysis of Contested Political Concepts
Semantic Network Analysis of Contested Political Concepts Open
This work presents methods for exploring the lexical environment of political concepts using interactive network visualisations of corpus-derived grammatical relations and word associations. The conceptual relations consist of part-of-spee…
View article: kbenoit/quanteda: CRAN v0.99.12
kbenoit/quanteda: CRAN v0.99.12 Open
Changes since v0.99.9 New Features Added methods for changing the docnames of tokens and dfm objects (#987). Bug fixes and stability enhancements The computation of tfidf has been more thoroughly described in the documentation for this fun…
View article: kbenoit/quanteda: CRAN release v0.99
kbenoit/quanteda: CRAN release v0.99 Open
New features Improvements and consoldiation of methods for detecting multi-word expressions, now active only through textstat_collocations(), which computes only the lambda method for now, but does so accurately and efficiently. (#753, #80…