117 citations · 194 across the 10 of their papers we have counts for
14 papers
Efficient Methods for Natural Language Processing: A Survey
Marcos Treviso, Ji-Ung Lee, Tianchu Ji +19
Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance mea…
Assisting Decision Making in Scholarly Peer Review: A Preference Learning Perspective
Nils Dycke, Edwin Simpson, Ilia Kuznetsov +1
Peer review is the primary means of quality control in academia; as an outcome of a peer review process, program and area chairs make acceptance decisions for each paper based on t…
Ranking Creative Language Characteristics in Small Data Scenarios
Julia Siekiera, Marius Köppel, Edwin Simpson +3
The ability to rank creative natural language provides an important general tool for downstream language understanding and generation. However, current deep ranking models require…
Predicting the Humorousness of Tweets Using Gaussian Process Preference Learning
Tristan Miller, Erik-Lân Do Dinh, Edwin Simpson +1
Most humour processing systems to date make at best discrete, coarse-grained distinctions between the comical and the conventional, yet such notions are better conceptualized as a…
Low Resource Multi-Task Sequence Tagging -- Revisiting Dynamic Conditional Random Fields
Jonas Pfeiffer, Edwin Simpson, Iryna Gurevych
We compare different models for low resource multi-task sequence tagging that leverage dependencies between label sequences for different tasks. Our analysis is aimed at datasets w…
Improving Factual Consistency Between a Response and Persona Facts
Mohsen Mesgar, Edwin Simpson, Iryna Gurevych
Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with facts describing the speaker's persona. These…
Scalable Bayesian Preference Learning for Crowds
Edwin Simpson, Iryna Gurevych
We propose a scalable Bayesian preference learning method for jointly predicting the preferences of individuals as well as the consensus of a crowd from pairwise labels. Peoples' o…
Interactive Text Ranking with Bayesian Optimisation: A Case Study on Community QA and Summarisation
Edwin Simpson, Yang Gao, Iryna Gurevych
For many NLP applications, such as question answering and summarisation, the goal is to select the best solution from a large space of candidates to meet a particular user's needs.…
Bayesian Heatmaps: Probabilistic Classification with Multiple Unreliable Information Sources
Edwin Simpson, Steven Reece, Stephen J. Roberts
Unstructured data from diverse sources, such as social media and aerial imagery, can provide valuable up-to-date information for intelligent situation assessment. Mining these diff…
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems
Steffen Eger, Gözde Gül Şahin, Andreas Rücklé +6
Visual modifications to text are often used to obfuscate offensive comments in social media (e.g., "!d10t") or as a writing style ("1337" in "leet speak"), among other scenarios. W…
A Bayesian Approach for Sequence Tagging with Crowds
Edwin Simpson, Iryna Gurevych
Current methods for sequence tagging, a core task in NLP, are data hungry, which motivates the use of crowdsourcing as a cheap way to obtain labelled data. However, annotators are…
Finding Convincing Arguments Using Scalable Bayesian Preference Learning
Edwin Simpson, Iryna Gurevych
We introduce a scalable Bayesian preference learning method for identifying convincing arguments in the absence of gold-standard rat- ings or rankings. In contrast to previous work…
Space Warps: I. Crowd-sourcing the Discovery of Gravitational Lenses
Philip J. Marshall, Aprajita Verma, Anupreeta More +20
We describe Space Warps, a novel gravitational lens discovery service that yields samples of high purity and completeness through crowd-sourced visual inspection. Carefully produce…
Dynamic Bayesian Combination of Multiple Imperfect Classifiers
Edwin Simpson, Stephen Roberts, Ioannis Psorakis +1
Classifier combination methods need to make best use of the outputs of multiple, imperfect classifiers to enable higher accuracy classifications. In many situations, such as when h…