(if you are interested in a PhD in any of the topics below contact me!)

Automated Fact-Checking

Prime minster said: ”Our government has halved youth unemployment!” True or False? Fact checking is one of the main tasks performed by journalists, especially in an era in which information sources abound. In our first paper we discussed the main challenges, namely the open domain nature of the task and the importance of context: temporal, geographical, conversational. We followed this up by a distantly supervised approach for fact-checking simple claims about statistical properties (with Sebastian Riedel)

Imitation Learning for Structured Prediction

Imitation learning is a paradigm originally developed in robotics that has been applied successfully to a variety of structured prediction tasks in NLP. Intuitively, it decomposes the usually complex output (e.g. a graph) to a sequence of actions that construct it. These actions are predicted by a suitalby trained policy. This framework has the advantage of being able to learn policies with non-decomposable loss functions without explicit enumeration of the output search space and has been applied successfully to a variety of applications, including information extraction (biomedical or web-based) and semantic parsing. (with Isabelle Augenstein and Jason Naradowsky)

Domain-independent Natural Language Generation

Currently weather sites host data (temperature, wind speed, humidity) concerning a multitude of cities and areas around the world. However, only a few locations feature textual weather forecasts as well. To automatically generate forecasts from the data itself, we aim to develop a domain-independent Natural Language Generation (NLG) framework by imitating generation policies from unaligned corpora. This will be applied to a variety of domains, as well as weather reports and data obtained from the Met Office. (EPSRC-funded with Gerasimos Lampouras, Sebastian Riedel and the Interaction Lab)