In short: I am highly skilled in developing, evaluating, and deploying Machine Learning (ML) systems using state of the art techniques. Excellent communicator, team player, and able to lead. I hold a Ph.D. from the Institute of Computer Science of the University of Oslo, focused on Natural Language Processing (NLP). I have a lot of experience in developing complex ML systems from the ground up from both successful startups as well as research institutions, and currently work in finance where I develop (and supervise the team developing) systems for claim automation, fraud detection and customer insight generation.
- 2020-Present: Senior Machine Learning Engingeer, Fremtind
R&D of systems for claim automation, fraud detection and customer insight generation. Tech lead responsabilities for a group of ML Engineers, data scientists and system developers. Key role at the crossroads between business and data, both as a coordinator (who should do what, when and how?) as well as an ambassador (why should we implement an ML system in this business process?).
- 2018-2020: Lead Data Scientist, Kindly
Research, development and deployment of the Natural Language Understanding (NLU) system powering the Kindly platform for chatbot creation. Responsibilities: Leading a team of 5 highly skilled data scientist, coordinating feature design across different teams (User Experience, Sales, DevOPS and so on), maintaining customer relations, and of course designing, developing and maintaning the actual ML platform.
- 2012-2019: PhD Research Fellow in Natural Language Processing (NLP), University of Oslo
My PhD work was partly funded by the CLARINO project, whose mission is facilitating access to NLP tools and resources for researchers in the Social Sciences and the Humanities. Key contributions of the project:
- Creating a scalable interchange format for the Language Analysis Portal
- Collaboration with the Department of Political Science, creating and researching the Talk of Norway data set
- 2014-2015: Researcher, CLARINO
I was on leave from my PhD for about a year to continue designing and developing the Language Analysis Portal, a user-friendly web application for combining NLP tools and annotating text with linguistic annotations leveraging the processing power of a large HPC cluster. I worked with a team of 4 developers at all levels, from database design and implementation to tool integration and graphical user interface.
- 2017: Researcher, NLPL
I was hired for 3 months as researcher to develop the Sherlock system. This is an open source release of the system I developed as a master student, which ranked first and second on the two tracks of the 2012 *SEM shared task on negation resolution. Sherlock was used as a tool to evaluate parser outputs in the 2017 EPE shared task.
- 2011: Developer, cXense
Internship at an NLP-centric startup, where I worked on live data visualization as well as Sentiment Analysis.
- 2010-2012: Teaching Assistant (TA), University of Oslo
I was a TA in the Algorithms and Data Structures class. I also TA'ed the introductory course on interaction design, where I was also tasked with developing obligatory assignments using Processing and Arduinos.
- Ph.d.: Language Technology, University of Oslo, 2019
Thesis focus: Design, implementation, and use of NLP tools and techniques in the Digital Humanities
Link: The Language Analysis Portal: Design, Implementation and Use
- M.Sc.: Computer Science, University of Oslo, 2012
Thesis focus: Negation Resolution and Sentiment Analysis.
Link: Sequence Labeling the Scope of Negation Using Dependency Features
Grade: A
- B.Sc.: Computer Science, University of Oslo, 2010
Lapponi, Emanuele; Søyland, Martin G.; Velldal, Erik & Oepen, Stephan (2018). The Talk of Norway: A Richly Annotated Corpus of the Norwegian Parliament, 1998–2016. Language Resources and Evaluation.
Eckart de Castilho, Richard; Ide, Nancy; Lapponi, Emanuele; Oepen, Stephan; Suderman, Keith; Velldal, Erik & Verhagen, Marc (2017). Representation and Interchange of Linguistic Annotation. An In-Depth, Side-by-Side Comparison of Three Designs, In Nathan Schneider & Nianwen Xue (ed.), Proceedings of the 11th Linguistic Annotation Workshop. Association for Computational Linguistics.
Lapponi, Emanuele; Oepen, Stephan & Øvrelid, Lilja (2017). EPE 2017: The Sherlock Negation Resolution Downstream Application, In Stephan Oepen (ed.), Proceedings of the 2017 Shared Task on Extrinsic Parser Evaluation at the Fourth International Conference on Dependency Linguistics and the 15th International Conference on Parsing Technologies. Association for Computational Linguistics.
Høyland, Bjørn; Godbout, Jean-François; Lapponi, Emanuele & Velldal, Erik (2014). Predicting Party Affiliations from European Parliament Debates, In Cristian Danescu-Niculescu-Miz; Jacob Eisenstein; Kathleen McKeown & Noah Smith (ed.), Proceedings of the ACL 2014 Workshop on Language Technologies and Computational Social Science. Association for Computational Linguistics.
Lapponi, Emanuele; Velldal, Erik; Oepen, Stephan & Knudsen, Rune Lain (2014). Off-Road LAF: Encoding and Processing Annotations in NLP Workflows, In Nicoletta Calzolari; Khalid Choukri; Thierry Declerck; Hrafn Loftsson; Bente Maegaard; Joseph Mariani; Asuncion Moreno; Jan Odijk & Stelios Piperidis (ed.), Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14). European Language Resources Association.
Elming, Jakob; Klerke, Sigrid; Lapponi, Emanuele; Martinez, Hector & Søgaard, Anders (2013). Down-stream effects of tree-to-dependency conversions, In Lucy Vanderwende; Hal Daumé III & Katrin Kirchhoff (ed.), Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics.
Lapponi, Emanuele; Velldal, Erik; Øvrelid, Lilja & Read, Jonathon (2012). UiO2: Sequence-labeling Negation Using Dependency Features, In Eneko Agirre; Johan Bos & Mona Diab (ed.), *SEM 2012: The First Joint Conference on Lexical and Computational Semantics --- Volume 1: Proceedings of the main conference and the shared task. Association for Computational Linguistics.