As of May 2019, I am an NLP Research Scientist at Samsung Articial Intelligence Center (SAIC) in Toronto, Canada. Previously I was a PostDoc at the University of Edinburgh working with Mirella Lapata on (multilingual) semantic parsing. My work has been focusing in particular on the graph-based formalisms for semantic parsing. I received my Ph.D. from the University of Edinburgh under the supervision of Bonnie Webber and Adam Lopez. My Ph.D. thesis explored different problems related to automatically detecting and representing negation in a cross-lingual setting. During my Ph.D. I also developped an interest in chatbots and had the fortune of leading the Edinburgh team in the 2016/2017 Amazon Alexa Challenge, where we developped Edina, an open-ended conversational agent, completely from scratch. Before moving to Canada, I have put this interest in practice by collaborating in HatchAI, a startup to develop AI solutions for financial services. Last but not least, I have a soft spot for East Asian Languages I have been studying and researching for a decade now.
- Neural Networks for Cross-lingual Negation Scope Detection Federico Fancellu, A. Lopez, B. Webber. arXiv preprint arXiv:1810.02156, 2018
- Talking to myself: self-dialogues as data for conversational agents Joachim Fainberg, Ben Krause, Mihai Dobre, Marco Damonte, Emmanuel Kahembwe, Daniel Duma, Bonnie Webber, Federico Fancellu. arXiv preprint arXiv:1809.06641, 2018
- Evaluating Machine Translation Performance on Chinese Idioms with a Blacklist Method Yutong Shao, Rico Sennrich, Bonnie Webber, Federico Fancellu. In LREC, 2018
- NegPar: a parallel corpus annotated for negation Qianchu Liu, Federico Fancellu, Bonnie Webber. In LREC, 2018
- Edina: Building an Open Domain Socialbot with Self-dialogues Ben Krause, Marco Damonte, Mihai Dobre, Daniel Duma, Joachim Fainberg, Federico Fancellu, Emmanuel Kahembwe, Jianpeng Cheng, Bonnie Webber, arXiv preprint arXiv:1709.09816, 2017
- Universal Dependencies to Logical Forms with Negation Scope Federico Fancellu, Siva Reddy, Adam Lopez, Bonnie Webber, In Proceeding of the SemBEAR workshop@EACL, 2017
- Neural Networks for Negation Cue Detection in Chinese Hangfeng He, Federico Fancellu, Bonnie Webber. In Proceedings of SemBEAR workshop@EACL, 2017.
- Detecting negation scope is easy, except when it isn't Federico Fancellu, Adam Lopez, and Bonnie Webber and Hangfeng He. In Proceedings of EACL, 2017.
- Neural networks for negation scope detection Federico Fancellu, Adam Lopez, and Bonnie Webber. In Proceedings of ACL, 2016.
- Translating negation: A Manual Eror Analysis Federico Fancellu and Bonnie Webber, In Proceedings of Ex-Prom (Extra-Propositional Aspects of Meaning in Computational Linguistics) workshop, 2015.
- Applying the semantics of negation to SMT through n-best list re-ranking Federico Fancellu and Bonnie Webber. In Proceedings of EACL, 2014
Students - University of Edinburgh
As second supervisor:
- Sorcha Gilroy(2018-2019): probabilistic models of graphs, graph parsing
- Lohith Anandan: "Coreference in Conversational Agents"
- Kristian Boda(now at BabylonHealth): "Imitating Rule-Based Discourse Using seq2seq Models"
- Leona Goebbels: "Evaluating Open-Domain Dialogue Systems on Coreference Generation"
- James Asamoah Michaelov(soon Ph.D.@USC): "UDepDRT: Converting from Universal Dependencies to Discourse Representation Theory"
- Amy Monkhouse(now at Depop):"Cross-lingual neural models for factuality detection"
- Qianchu Liu(now Ph.D.@Cambridge):"Annotation projection of textual negation"
- Parinaz Mehr:"RNN for negation scope detection in BioMedical texts"
- Jingfeng Liu: Jingfeng and I are working together on cross-lingual semantic parsing
- Hengfeng He(now Ph.D.@UPenn): Hengfeng and I worked together on negation detection in Chinese
- Mirella Lapata - University of Edinburgh
- Adam Lopez - University of Edinburgh
- Siva Reddy - Stanford University
- Bonnie Webber - University of Edinburgh