AMDG

Welcome! 👋

31 Mar 20258 min read

Hi friends, I’m Silviu. Get in touch!

Publications | Google Scholar Semantic Scholar ORCiD Web of Science

✝ Catholic, husband, and computer scientist;
🎓 PhD in Data Science from the University of Edinburgh (SMASH group); MSc in Computer Science from the University of Oxford;
💻 Worked as a software engineer in start-ups; Applied Scientist for Amazon; Research Scientist for Huawei; and Principal Engineer for Samsung.
📚 Interested in Theology and Philosophy; and Artificial Intelligence.

From the blog

My recent work has focused on the safety of AI agents. For instance, in a recent paper (EMNLP 2024), we introduce a parameter-efficient guardrailing method for large language models. I am also interested in how safety standards are influenced by socio-demographic factors. Further interests in this direction include training AI agents, particularly in a way that maximises multilingual performance and avoids memorising harmful biases; and evaluating them, particularly on tasks where the correct output is a function of socio-demographic factors (such a task is commomnsense inference).

News

Check out more news here.

Work

  • 2024: Principal Engineer at Samsung R&D Institute (UK)
    I’ve recently been working on LLM guardrailing. For instance, check out our paper, LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models (EMNLP 2024)
  • 2022 - 2024: Applied Scientist at Amazon Alexa AI
    I’ve worked on improving the ability of large language models (LLMs) to generate responses that would provide Alexa customers with a more delightful experience.
  • 2021: Applied Scientist (Intern) at Amazon Alexa AI
  • 2020: Research Scientist (Intern) at Huawei
    I worked with Haytham Assem and Sourav Dutta on learning transformations between monolingual word embedding spaces, to enable unsupervised translation and transfer learning to low-resource languages. Check out our COLING 2022 paper based on this work.
  • 2019: Researcher at Frontier Development Lab
    At Frontier Developemnt Lab, we built a flood segmentation model. In the process, we collaborated with the European Space Agency and UNICEF. The model has now been deployed by SpaceX on an actual satellite 🛰. Our work was covered by this post from the University of Oxford; and by several media outlets: 1, 2), 3, 4, 5. Check out our Nature (Scientific Reports) paper and the video of the rocket launch 🚀
  • 2014 - 2017: Engineer at VisualDNA and TheySay
    During this time, I was an engineer at two tech startups. First, a software engineer at VisualDNA, a data science and management platform, where I worked on data aggregation and reporting using Scala and the Scalding interface to Hadoop. After VisualDNA, I spent some time as a contractor. Next, I was an artificial intelligence engineer at TheySay, a startup providing text analytics services, where I used technologies such as Scala and MongoDB. Both startups were acquired (after I left), see this article about VisualDNA, and this one about TheySay.
  • 2012: Guest Researcher at the National Institute for Standards and Technology
    I worked with Bruce Miller on extending LaTeXML, a TeX parser that he wrote in Perl. The goal of my extenssion was to convert TikZ graphics to SVG. See this paper that mentions my work.

Education

  • 2018 - 2023: PhD in Data Science at the University of Edinburgh
    Check out my thesis, Computational Sarcasm Detection and Understanding in Online Communication.
    In summary, I used computational methods to detect and understand the phenomenon of sarcasm, as it is manifested in online textual communication, together with my supervisors, Walid Magdy, Bonnie Webber, and Maria Wolters.
    More specifically, I built a dataset of texts annotated for sarcasm (ACL 2020 paper), introduced sarcasm detection models (ACL 2019 paper), and also organised a competition encouraging the community to build such models (SemEval 2022 paper). I showed that people of similar socio-demographic backgrounds understand each other’s sarcasm more often than people of dissimilar backgrounds (CSCW 2022 paper). Finally, I built a sarcastic chatbot (EMNLP 2021 demo), and investigated when it is appropriate for chatbots to be sarcastic, and how they should formulate their utterances (ACL 2022 paper).
    Along the way, I had fun as an intern at Frontier Development Lab in 2019 (20201 Nature (Scientific Reports) paper), at Huawei in 2020 (COLING 2022 paper), and at Amazon Alexa AI in 2021 (paper in the baking 👨🏻‍🍳). See below, in the Work section.
  • 2017 - 2018: MRes in Data Science at the University of Edinburgh
    I used computational methods to detect the presence of sarcasm in tweets, together with my supervisor, Walid Magdy.
  • 2012 - 2013: MSc in Computer Science at the University of Oxford
    I worked with Phil Blunsom on building character-level language models for the Romanian language using recurrent neural networks.
  • 2009 - 2012: BSc in Computer Science at Jacobs University Bremen
    This is where my interest in natural language processing was triggered, working with Michael Kohlhase.

Media Coverage

Patents

My Google Patents page is here.

  • Processing communications in a computing arrangement for semantic understanding and interpretation of code-switching (html)
    Sourav Dutta, Silviu Vlad Oprea, Haytham Assem, and Hu Peng
    Patent WO2022069030A1 issued from application PCT/EP2020/077336. 2022.

Publications

Check the full list of publications on my Google Scholar profile.

Safety and bias of generative models:

  • LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models (pdf)
    Hayder Elesedy, Pedro M. Esperança, Silviu Vlad Oprea, and Mete Ozay
    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2024.

Figurative language comprehension:

  • Sarcasm Detection is Way Too Easy! An Empirical Comparison of Human and Machine Sarcasm Detection (pdf)
    Ibrahim Abu Farha, Steven Wilson, Silviu Vlad Oprea, and Walid Magdy
    Findings of the Association for Computational Linguistics. 2022.

  • SemEval-2022 Task 6: iSarcasmEval, Intended Sarcasm Detection in English and Arabic (pdf, video)
    Ibrahim Abu Farha, Silviu Vlad Oprea, Steven Wilson, and Walid Magdy
    Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022). 2022.

  • iSarcasm: A Dataset of Intended Sarcasm (pdf, video)
    Silviu Vlad Oprea, and Walid Magdy
    Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.

  • Exploring Author Context for Detecting Intended vs Perceived Sarcasm (pdf, video)
    Silviu Vlad Oprea, and Walid Magdy
    Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019.

Computational social science:

  • Should a Chatbot be Sarcastic? Understanding User Preferences Towards Sarcasm Generation (pdf, video)
    Silviu Vlad Oprea, Steven Wilson, and Walid Magdy
    Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. 2022.

  • The Effect of Sociocultural Variables on Sarcasm Communication Online (pdf, html)
    Silviu Vlad Oprea, and Walid Magdy
    Proceedings of the ACM on Human-Computer Interaction. 2020.

  • Chandler: An Explainable Sarcastic Response Generator (pdf, video)
    Silviu Vlad Oprea, Steven Wilson, and Walid Magdy
    Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2021.

Multilinguality:

  • Multi-Stage Framework with Refinement Based Point Set Registration for Unsupervised Bi-Lingual Word Alignment (pdf)
    Silviu Vlad Oprea, Sourav Dutta, and Haytham Assem
    Proceedings of the 29th International Conference on Computational Linguistics. 2022.

Computer vision:

  • Towards global flood mapping onboard low cost satellites with machine learning (html)
    Gonzalo Mateo-Garcia*, Joshua Veitch-Michaelis*, Lewis Smith*, Silviu Vlad Oprea, Guy Schumann, Yarin Gal, Atılım Güneş Baydin, and Dietmar Backes
    Nature (Scientific Reports). 2021.

* indicates equal contribution.

Teaching

  • 2021: Lab demonstrator for Text Technologies in Data Science at the University of Edinburgh.
  • 2010 and 2011: Teaching assistant for Programming in C/C++ at Jacobs University Bremen.

Talks

This list does not include conference presentations of my papers.

2023 and 2024:

  • Talk entitled “Socio-demographic considerations in natural language processing: case studies from investigating sarcasm​”, at Sabancı University, Türkiye (online).
  • Talk about my work on sarcasm detection and understanding, at Oakland University, MI, USA (online).
  • Talk about my work on sarcasm detection and understanding, at the Technical University of Cluj-Napoca, Romania (online).

Graph View

Backlinks

  • No backlinks found