• Publications
  • Influence
The SENSEI Annotated Corpus: Human Summaries of Reader Comment Conversations in On-line News
A method is described to support humans in authoring conversation overview summaries and a publicly available corpus is presented – the first of its kind – of news articles plus comment sets, each multiply annotated, according to the method, with conversation Overview summaries. Expand
FlickLing: a Multilingual Search Interface for Flickr
The user logs generated are described, which has been used as a data source for the iCLEF 2008 log analysis task and contain over 5,000 complete search sessions made by over 200 users with a wide variety of language skills. Expand
Summarizing Multi-Party Argumentative Conversations in Reader Comment on News
An issue-centred scheme for analysing and graphically representing argument in reader comment discussion in on-line news is proposed and summaries capturing the argumentative nature of reader comment can be generated from this graphical representation. Expand
Contemporary cultures of display
Focusing on the place of art in contemporary culture, this work discusses museums, galleries and exhibitions in Western Europe and the USA. It encourages readers to reflect on their own experiencesExpand
Large-scale interactive evaluation of multilingual information access systems: the iCLEF Flickr challenge
The large-scale interactive evaluation of multilingual information access systems, as part of the Cross-Language Evaluation Forum evaluation campaign, is discussed, which is based on interaction with content from Flickr, the popular online photo-sharing service. Expand
Automatic label generation for news comment clusters
It is illustrated how cluster labels can be used to generate cluster summaries and two alternative sum- mary formats are presented: a pie chart summary and an ab- stractive summary. Expand
Assessing the Comparability of News Texts
An annotation methodology, similar to that used in summarization evaluation, is proposed to allow us to identify and quantify shared content at the subsentential level in news text pairs and report a preliminary exercise to assess this method. Expand
Simulating Cub Reporter Dialogues: The collection of naturalistic human-human dialogues for information access to text archives
This paper describes a dialogue data collection experiment and resulting corpus for dialogues between a senior mobile journalist and a junior cub reporter back at the office, and the methodology adopted for creating such a corpus and the corpus that is currently under construction. Expand
Integrating NLP Tools to Support Information Access to News Archives
The described Cubreporter, a project which investigates the use of advanced natural language processing techniques to enhance access to a news archive for the specific purpose of background writing, and the description of the overall functionalities of the prototype. Expand
Policing LGBTIQ people in rural spaces: emerging issues and future concerns
This article argues identifying as lesbian, gay, bisexual, transgender, intersex, queer and/or questioning (LGBTIQ) in rural spaces can produce specific types of policing experiences. While someExpand