EPSRC DTG-funded PhD studentship
PhD project “Recognizing Trust in Natural Language”
Applications are invited for a PhD studentship in the EPSRC DTP-funded project “Recognizing Trust in Natural Language” in the areas of computer models of argument, natural language processing and big data. Processing and evaluation of trust in speaker’s credibility is crucial for many different sectors of industry such as e.g. reviews that provide the main source of information for users of online shopping networks such as Amazon and eBay, and travel sites as TripAdvisor. The goal of the project is to build a prototype of a system for semi-automatic identification and exploration through big maps of arguments linked to the credibility of their providers.
You can apply by sending a CV with a covering letter to Dr. Katarzyna Budzynska (k.budzynska (at) dundee.ac.uk)
Application deadline: 18 Dec 2014
Starting date of the project: mid 2015
1. Main Goal
Trust in the speaker’s character, his credibility or ethos, is one of the most important and influential elements of real-life practice — from everyday communication, social debates, news, reviews for online sellers or travel sites, legal discourse to human intelligence. Being able to properly evaluate an information source is crucial for deciding whether or not we should believe news report provided by a journalist or a blogger, or whether or not we should convict a suspect on a basis of a given witness testimony.
The goal of the project is to understand how people express trust in natural language and to apply methods and techniques of computational linguistics and natural language processing to argument mining, i.e. to extracting of trust and credibility from resources of natural language texts. The project’s output will be a prototype of a system for semi-automatic processing of trust and exploring through big maps of arguments linked to the credibility of their providers.
The workplan assumes that the project will first develop an annotated corpus applying the Inference Anchoring Theory standard and then provide a demonstrator of Ethos Mining tool for semi-automated extraction of arguments supporting and attacking ethos. We will also work on integrating the tool with other ARG-tech’s tools for argument mapping, navigation and exploration.
2. Links with Industry
Processing and evaluation of trust in speaker’s credibility is crucial for many different sectors of industry. For example, reviews provide the main source of information for users of online shopping networks such as Amazon and eBay, and travel sites as TripAdvisor. Yet analysing and structuring vast amounts of specialized data can be a very expensive task in terms of time and effort. The main technological challenge is to enable processing big datasets in a more structured and semi-automatic way. This project will be run in parallel and in a close cooperation with a research assistant who will start at the same time on a TSB-funded project “Argument Analytics” which involves an industrial partner.
3. Prospects for Further Career Path
Different funding bodies are starting to recognise the potential and importance of innovation and development in the area of big data. The Scottish Funding Council (SFC) has just funded ‘Big data’ innovation centre setting to add over 300 jobs and £150m to Scottish economy (read here). Both EPSRC and EU (H2020) are investing a large amounts of funds for the calls addressing the area of big data:
Big Data creates numerous opportunities for driving research and development (…) [RCUK] recognises the enormous potential of Big Data for the UK economy with a total sum of £189 million to invest in its exploitation.
UK Research Councils on Big Data; available at here
Worldwide Big Data technology and services are expected to grow from €2.4 billion in 2010 to €12.7 billion in 2015. The challenge is to strengthen Europe’s position as provider of products and services based on digital content and data.
EU Council Decision Establishing the Specific Programme Implementing HORIZON 2020.
4. Environment and Support
The studentship will be held in the Centre for Argument Technology, ARG-tech, in the School of Computing at the University of Dundee. The research will be supervised by Dr. Katarzyna Budzynska, and held in close cooperation with Prof. Chris Reed and a research assistant who will start at the same time on a TSB-funded project “Argument Analytics” (involving an industrial partner), as well as with our collaborators in France, Germany, Poland and Switzerland.
ARG-tech has built a reputation on balancing high quality theoretical research with robust and reliable software engineering. Its software is in use in thousands of schools, colleges and universities in over 60 countries around the world. The group of ARG-tech is working with users and major players in domains such as law, mediation, government, media and education, and the tools we are building are regularly demonstrated to groups within these domains.
The student will be working in close cooperation with the international network of our collaborators in IRIT Toulouse (discourse processing and opinion mining, computational linguistics); University of Potsdam (discourse generation and speech act theory, computational linguistics); Polish National Academy of Sciences at Warsaw (logic and philosophy of communication); and Università della Svizzera italiana in Lugano (pragmatics of financial communication, communication studies).
At the most recent RAE, the research of the School of Computing in Dundee was rated fourth in Scotland, with two thirds of its research rated world leading or internationally excellent (4* or 3*). Dundee has been ranked amongst the top places in the world for scientists to work (The Scientist), has one of the lowest costs of living in the UK, and has been voted one of the best universities in the UK for student experience.
5. Requirements and Conditions
The candidate should have at least bachelor degree, preferably in linguistics, computational linguistics, computer science, artificial intelligence or related areas. Programming experience would be an advantage. According to EPSRC regulations, an applicant has to be current UK resident student. Interest in communication and natural language in either computational, linguistic or philosophical settings would be beneficial.
The project will start in 2015 and will run for 3.5 years.
Stipendary payments are at EPSRC levels (13,863 GBP for academic year 2014/15; tax-free). Applicants should meet the EPSRC’s eligibility requirements (see www.epsrc.ac.uk).
Applicants should send a CV with a covering letter to Dr. Katarzyna Budzynska, School of Computing, University of Dundee, Dundee DD1 4HN, or by email to k.budzynska (at) dundee.ac.uk