Stephen Wan

Automatic English-Chinese name transliteration for development of multilingual resources

In this paper, we describe issues in the translation of proper names from English to Chinese which we have faced in constructing a system for multilingual text generation supporting both languages. We introduce an algorithm for mapping from English names to Chinese characters based on (1) heuristics about relationships between English spelling and pronunciation, and (2) consistent relationships between English phonemes and Chinese characters.

Generating overview summaries of ongoing email thread discussions

The tedious task of responding to a backlog of email is one which is familiar to many researchers. As a subset of email management, we address the problem of constructing a summary of email discussions. Specifically, we examine ongoing discussions which will ultimately culminate in a consensus in a decision-making process. Our summary provides a snapshot of the current state-of-affairs of the discussion and facilitates a speedy response from the user, who might be the bottleneck in some matter being resolved. We present a method which uses the structure of the thread dialogue and word vector techniques to determine which sentence in the thread should be extracted as the main issue. Our solution successfully identifies the sentence containing the issue of the thread being discussed, potentially more informative than subject line.

Improving Grammaticality in Statistical Sentence Generation: Introducing a Dependency Spanning Tree Algorithm with an Argument Satisfaction Model

Abstract-like text summarisation requires a means of producing novel summary sentences. In order to improve the grammaticality of the generated sentence, we model a global (sentence) level syntactic structure. We couch statistical sentence generation as a spanning tree problem in order to search for the best dependency tree spanning a set of chosen words. We also introduce a new search algorithm for this task that models argument satisfaction to improve the linguistic validity of the generated tree. We treat the allocation of modifiers to heads as a weighted bipartite graph matching (or assignment) problem, a well studied problem in graph theory. Using BLEU to measure performance on a string regeneration task, we found an improvement, illustrating the benefit of the spanning tree approach armed with an argument satisfaction model.

Generating Personal Travel Guides - And Who Wants Them?

In this paper we describe a system that generates synthesized web pages as a travel guide through integrating a discourse planner with a document retrieval system. We then present our investigation on whether the guide generated by such a system is actually preferred by users over a more general guide.

Listening to the community: social media monitoring tasks for improving government services

We present a preliminary analysis of the tasks and information needs of users performing social media monitoring to improve government services. In general, our aim is to explore how text analysis tools can support a social media monitoring task in the government context. We find that, in this context, social media monitoring is a complex activity. Social media monitors not only perform traditional media monitoring tasks, but they also take specific actions to provide an improved service, predominantly by checking and vetting information contributed by the wider online community. In our analysis, we found a number of specific information-based actions performed in order to determine how one should respond to a particular social media post.

Using Thematic Information in Statistical Headline Generation

We explore the problem of single sentence summarisation. In the news domain, such a summary might resemble a headline. The headline generation system we present uses Singular Value Decomposition (SVD) to guide the generation of a headline towards the theme that best represents the document to be summarised. In doing so, the intuition is that the generated summary will more accurately reflect the content of the source document. This paper presents SVD as an alternative method to determine if a word is a suitable candidate for inclusion in the headline. The results of a recall based evaluation comparing three different strategies to word selection, indicate that thematic information does help improve recall.

Generating Personal Travel Guides from Discourse Plans

This paper describes a system that delivers travel guides tailored to individual needs. It does so by integrating a discourse planner with a system for querying the web and generating synthesised web pages using document prescriptions. We show by way of example how a user model can lead to a personal travel guide, and show what this might look like in different media. We briefly describe the investigations we are undertaking to determine the utility of such approaches.

Improving government services with social media feedback

Social media is an invaluable source of feedback not just about consumer products and services but also about the effectiveness of government services. Our aim is to help analysts identify how government services can be improved based on citizen-contributed feedback found in publicly available social media. We present ongoing research for a social media monitoring interactive prototype with federated search and text analysis functionality. The prototype, developed to fit the workflow of social media monitors in the government sector, collects, analyses, and provides overviews of social media content. It facilitates relevance judgements on specific social media posts to decide whether or not to engage online. Our user log analysis validates the original design requirements and indicates ongoing utility to our federated search approach.

Invited paper: Supporting browsing-specific information needs: Introducing the Citation-Sensitive In-Browser Summariser

Practitioners and researchers need to stay up-to-date with the latest advances in their fields, but the continual growth in the amount of literature available makes this task increasingly difficult. In this article, we describe the Citation-Sensitive In-Browser Summariser (CSIBS), a new research tool to help manage the literature browsing task. The design of CSIBS was based on a user requirements analysis which identified the information needs that biomedical researchers commonly encounter when browsing through academic literature. CSIBS supports researchers in their browsing tasks by presenting both a generic and a tailored preview about a citation at the point at which they encounter it. This information is aimed at helping the reader determine whether or not to invest the time in exploring the cited article further, thus alleviating information overload. Feedback from biomedical researchers indicates that CSIBS facilitates this relevance judgement task, and that the interface and previews are informative and easy to use.

In-Browser Summarisation: Generating Elaborative Summaries Biased Towards the Reading Context

We investigate elaborative summarisation, where the aim is to identify supplementary information that expands upon a key fact. We envisage such summaries being useful when browsing certain kinds of (hyper-)linked document sets, such as Wikipedia articles or repositories of publications linked by citations. For these collections, an elaborative summary is intended to provide additional information on the linking anchor text. Our contribution in this paper focuses on identifying and exploring a real task in which summarisation is situated, realised as an In-Browser tool. We also introduce a neighbourhood scoring heuristic as a means of scoring matches to relevant passages of the document. In a preliminary evaluation using this method, our summarisation system scores above our baselines and achieves a recall of 57% annotated gold standard sentences.