• Publications
  • Influence
A survey of trust in social networks
This article presents the first comprehensive review of social and computer science literature on trust in social networks and discusses recent works addressing three aspects of social trust: trust information collection, trust evaluation, and trust dissemination.
Planning Text for Advisory Dialogues: Capturing Intentional and Rhetorical Information
It is argued that, to handle explanation dialogues successfully, a discourse model must include information about the intended effect of individual parts of the text on the hearer, as well as how the parts relate to one another rhetorically.
Using Dependency-Based Features to Take the ’Para-farce’ out of Paraphrase
A machine learning approach is proposed to be used to filter out inconsistent novel sentences, or False Paraphrases, using the Microsoft Research Paraphrase corpus and investigating whether features based on syntactic dependencies can aid in this task.
Improving Grammaticality in Statistical Sentence Generation: Introducing a Dependency Spanning Tree Algorithm with an Argument Satisfaction Model
This work couch statistical sentence generation as a spanning tree problem in order to search for the best dependency tree spanning a set of chosen words and introduces a new search algorithm for this task that models argument satisfaction to improve the linguistic validity of the generated tree.
Classifying microblogs for disasters
This work addresses the issue of filtering massive amounts of Twitter data to identify high-value messages related to disasters, and to further classify disaster-related messages into those pertaining to particular disaster types, such as earthquake, flooding, fire, or storm.
Automatically summarising Web sites: is there a way around it?
This work suggests a new approach, which relies on the structure of hypertext and the way people describe information in it, which offers an easy way to produce unbiased, coherent, and contentfull summaries of Web sites.
An Effective Transition-based Model for Discontinuous NER
This work proposes a simple, effective transition-based model with generic neural encoding for discontinuous NER that can effectively recognize discontinuous mentions without sacrificing the accuracy on continuous mentions.
Talking about your health to strangers: understanding the use of online social networks by patients
It is found that, consistent with previous research, most patients were seeking information about their medical condition online, while, at the same time, still interacting with health professionals to talk about sensitive information and complex issues.
Segmenting Email Message Text into Zones
Zebra is described, an SVM-based system for segmenting the body text of email messages into nine zone types based on graphic, orthographic and lexical cues and performs this task with an accuracy of 87.01%.
User Modeling in Text Generation