Description: Large amounts of text are added to the Web daily from social media, web-based commerce, scientific papers, eGovernment consultations, etc. Such texts are used to make decisions in the sense that people read the texts, carry out some informal analysis, and then (in the best case) make a decision; for example, a consumer might read the comments on an Amazon website about a camera before deciding what camera to buy. The problem is that such information is distributed, unstructured, and not cumulative. In addition, the argument structure - justifications for a claim and criticisms - might be implicit or explicit within some document, but harder to discern across documents. The sheer volume of information overwhelms users. Given all these problems, reasoning about arguments on the web is currently unfeasible. A solution to these problems would be to develop tools to aggregate, synthesize, structure, summarize, and reason about arguments in texts. Such tools would enable users to search for particular topics and their justifications, trace through the argument (justifications for justifications and so on), as well as to systematically and formally reason about the graph of arguments. By doing so, a user would have a better, more systematic basis for making a decision. However, deep, manual analysis of texts is time-consuming, knowledge intensive, and thus unscalable. To acquire, generate, and transmit the arguments, we need scalable machine-based or machine-supported approaches to extract arguments. The application of tools to mine arguments would be very broad and deep given the variety of contexts where arguments appear and the purposes they are put to.
In this context, the goal of the Postdoctoral position is to address the following challenges: - define algorithms for automatically identifying arguments in texts. The goal is to detect, at an abstract level, the argumentative structures in texts. In addition, challenges like the automated discrimination between argumentative and non argumentative text units, and the identification of reused, but manipulated, arguments which convey a different meaning than what was intended by their source, will be addressed. - Propose intra-argument mining algorithms, to automatically detect the internal structure of arguments. The goal is to analyze and formalize the internal structure of the retrieved arguments, i.e., the identification of the relations that may hold between the arguments’ premises and conclusion, using machine learning methods, including deep learning ones. - Propose inter-argument mining algorithms, to automatically predict what are the relations holding between the arguments identified in the first stage. This is an extremely complex task, as it involves high-level knowledge representation and reasoning issues. The relations between the arguments may be of heterogeneous nature, like attack, support or entailment.
References: - Proceedings of the Workshop on Frontiers and Connections between Argumentation Theory and Natural Language Processing http://ceur-ws.org/Vol-1341/ - Lippi, M., Torroni, P., Argumentation Mining: State of the Art and Emerging Trends , ACM Transactions on Internet Technology, 2015. - Elena Cabrio, Serena Villata :A natural language bipolar argumentation approach to support users in online debate interactions†. Argument & Computation 4(3) : 209-230 (2013) - Available resources for Argument mining http://argumentationmining.disi.unibo.it/resources.html
Skills and profile: • Ph.D. in Computer Science, Artificial Intelligence or Computational Linguistics is required (obtained less than 4 years ago). • Programming skills. • Strong knowledge of Natural Language Processing. • Knowledge of logic (propositional, first order) is preferred. • Fluent English required, both oral and written. French is not mandatory.
Hosting team: WIMMICS (http://wimmics.inria.fr/) is a research team of Université Côte d’Azur (UCA). The research fields of this team are graph-oriented knowledge representation, reasoning and operationalization to model and support actors, actions and interactions in web-based epistemic communities.
Location: I3S laboratory, Sophia Antipolis, France. Duration: 24 months Salary: 3000 euros/month (gross salary)
Applications : a curriculum vitae together with a motivation letter should be sent to Serena Villata: villata at i3s.unice.fr and Elena Cabrio: elena.cabrio at unice.fr . Deadline for applications: May 30th, 2017. -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 5747 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20170505/c1a9d027/attachment.txt>