arXiv subjects

Cecile Paris

Publications and source records attributed to Cecile Paris.

42 records · Page 3Linked to original sources

arXiv2018

Cross-Target Stance Classification with Self-Attention Networks

In stance classification, the target on which the stance is made defines the boundary of the task, and a classifier is usually trained for prediction on the same target. In this work, we explore the potential for generalizing classifiers between different targets, and propose a neural model that can apply what has been learned from a source target to a destination target. We show that our model can find useful information shared between relevant targets which improves generalization in certain scenarios.

cs.CL↗

arXiv2018

Benchmarking Clinical Decision Support Search

Finding relevant literature underpins the practice of evidence-based medicine. From 2014 to 2016, TREC conducted a clinical decision support track, wherein participants were tasked with finding articles relevant to clinical questions posed by physicians. In total, 87 teams have participated over the past three years, generating 395 runs. During this period, each team has trialled a variety of methods. While there was significant overlap in the methods employed by different teams, the results were varied. Due to the diversity of the platforms used, the results arising from the different techniques are not directly comparable, reducing the ability to build on previous work. By using a stable platform, we have been able to compare different document and query processing techniques, allowing us to experiment with different search parameters. We have used our system to reproduce leading teams runs, and compare the results obtained. By benchmarking our indexing and search techniques, we can statistically test a variety of hypotheses, paving the way for further research.

cs.IR↗

arXiv2017

Automated text summarisation and evidence-based medicine: A survey of two domains

The practice of evidence-based medicine (EBM) urges medical practitioners to utilise the latest research evidence when making clinical decisions. Because of the massive and growing volume of published research on various medical topics, practitioners often find themselves overloaded with information. As such, natural language processing research has recently commenced exploring techniques for performing medical domain-specific automated text summarisation (ATS) techniques-- targeted towards the task of condensing large medical texts. However, the development of effective summarisation techniques for this task requires cross-domain knowledge. We present a survey of EBM, the domain-specific needs for EBM, automated summarisation techniques, and how they have been applied hitherto. We envision that this survey will serve as a first resource for the development of future operational text summarisation techniques for EBM.

cs.CL↗

arXiv2013

A Trust Model Based Analysis of Social Networks

In this paper, we analyse the sustainability of social networks using STrust, our social trust model. The novelty of the model is that it introduces the concept of engagement trust and combines it with the popularity trust to derive the social trust of the community as well as of individual members in the community. This enables the recommender system to use these different types of trust to recommend different things to the community, and identify (and recommend) different roles. For example, it recommends mentors using the engagement trust and leaders using the popularity trust. We then show the utility of the model by analysing data from two types of social networks. We also study the sustainability of a community through our social trust model. We observe that a 5% drop in highly trusted members causes more than a 50% drop in social capital that, in turn, raises the question of sustainability of the community. We report our analysis and its results.

cs.SI↗

arXiv1996

Building Knowledge Bases for the Generation of Software Documentation

Automated text generation requires a underlying knowledge base from which to generate, which is often difficult to produce. Software documentation is one domain in which parts of this knowledge base may be derived automatically. In this paper, we describe \drafter, an authoring support tool for generating user-centred software documentation, and in particular, we describe how parts of its required knowledge base can be obtained automatically.

cmp-lg↗

arXiv1996

Two Sources of Control over the Generation of Software Instructions

This paper presents an analysis conducted on a corpus of software instructions in French in order to establish whether task structure elements (the procedural representation of the users' tasks) are alone sufficient to control the grammatical resources of a text generator. We show that the construct of genre provides a useful additional source of control enabling us to resolve undetermined cases.

cmp-lg↗