About me

I am a computational linguist. I have defended my doctoral thesis on grounded language generation and understanding with neural language models. The aim was to combine linguistic representations with uncertain perceptual representations in a single framework.

In addition to my research, as a PhD student, I was the teaching assistant for following courses in Master in Language Technology (MLT) programme at GU and co-supervisor in a few master projects.

  • Artificial intelligence: Cognitive systems (Formerly: “Embodied and Situated Language Processing”) (November-January, 2017, 2018, 2019, 2020)
  • Statistical Methods for NLP (January to March, 2016, 2017, 2018)
  • Computational Semantics (April-June 2016, 2017, 2018, 2019, 2020)
  • Dialog Systems I (2016)

Since January 2021, I have joined the DocuSign AI group in Sweden. Since then, my focus has shifted to more product-driven research on applications of large language models (LLMs) in a wide range of machine learning tasks in our development for legal language understanding (information extraction, text classification, few-shot learning, active learning and multi linguality).

List of publications

My google scholar page might have the latest updated list. Here is an extended list on GU library. Or, maybe you find the following easier direct access to additional materials and codes:

  • Linnea Strand, Robert Rhys Thomas, Simon Dobnik, Mehdi Ghanimifard. “Topic modelling for a virtual librarian assistant tool.” Proceedings of WatchDial - Semdial 2020: The 24the Workshop on the Semantics and Pragmatics of Dialogue. 2020. pdf
  • Magdalena Sandahl, Simon Dobnik, Mehdi Ghanimifard. “A corpus of Swedish conversations with a librarian.” Proceedings of WatchDial - Semdial 2020: The 24the Workshop on the Semantics and Pragmatics of Dialogue. 2020. pdf
  • José Miguel Cano Santín, Simon Dobnik, Mehdi Ghanimifard. “Fast visual grounding in interaction: bringing few-shot learning with neural networks to an interactive robot.” Proceedings of Conference on Probability and Meaning (PaM-2020), Gothenburg, Sweden. 2020. pdf
  • Simon Dobnik, Mehdi Ghanimifard. “Spatial descriptions on a functional-geometric spectrum: the location of objects.” Spatial Cognition XII: Proceedings of the 12th International Conference, Spatial Cognition 2020, Riga, Latvia. 2020. pdf
  • Mehdi Ghanimifard “Why the pond is not outside the frog? Grounding in contextual representations by neural language models” Doctoral thesis in Computational Linguistics at Department of Philosophy, Linguistics and Theory of Science. The Centre for Linguistic Theory and Studies in Probability (CLASP), University of Gothenburg. 2020. url source
  • Ghanimifard, Mehdi, and Simon Dobnik. “What goes into a word: generating image descriptions with top-down spatial knowledge.” Proceedings of the 12th International Conference on Natural Language Generation. 2019. pdf webpage
  • Ek, Adam, and Mehdi Ghanimifard. “Synthetic Propaganda Embeddings to Train a Linear Projection.” Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda. 2019. pdf
  • Santín, José Miguel Cano, Simon Dobnik, and Mehdi Ghanimifard. “Interactive visual grounding with neural networks.” pdf
  • Ghanimifard, Mehdi, and Simon Dobnik. “What a neural language model tells us about spatial relations.” Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP). 2019. pdf code
  • Ghanimifard, Mehdi, and Simon Dobnik. “Knowing when to look for what and where: Evaluating generation of spatial descriptions with adaptive attention.” Proceedings of the European Conference on Computer Vision (ECCV). 2018. pdf code
  • Bizzoni, Yuri, and Mehdi Ghanimifard. “Bigrams and BiLSTMs Two neural networks for sequential metaphor detection.” Proceedings of the Workshop on Figurative Language Processing. 2018. pdf code
  • Dobnik, Simon, Mehdi Ghanimifard, and John Kelleher. “Exploring the functional and geometric bias of spatial relations using neural language models.” (2018). pdf code
  • Bizzoni, Yuri, Stergios Chatzikyriakidis, and Mehdi Ghanimifard. ““Deep” Learning: Detecting Metaphoricity in Adjective-Noun Pairs.” Proceedings of the Workshop on Stylistic Variation. 2017. pdf code webpage
  • Ghanimifard, Mehdi, and Simon Dobnik. “Learning to Compose Spatial Relations with Grounded Neural Language Models.” IWCS 2017-12th International Conference on Computational Semantics-Long papers. 2017. pdf code
  • Ghanimifard, Mehdi, and Richard Johansson. “Enriching Word Sense Embeddings with Translational Context.” Proceedings of the International Conference Recent Advances in Natural Language Processing. 2015. pdf code