David R. Mortensen
Language Technologies Institute, School of Computer Science, Carnegie Mellon University.
5407 Gates Hillman Complex
Language Technologies Institute
Carnegie Mellon University
5000 Forbes Ave
Pittsburgh, PA 15213
I am a computational linguist interested in phonology, morphology, language change, linguistic typology, and human-in-the-loop computation. I am currently an Assistant Research Professor in the Language Technologies Institute, which is part of Carnegie Mellon University’s School of Computer Science. Before coming to CMU, I was an Assistant Professor in the Department of Linguistics at the University of Pittsburgh.
I did my graduate work at the University of California, Berkeley, where I recieved a PhD in Linguistics for a thesis on theoretical phonology. At the same time, I was working on various computational projects relating to language documentation and comparative reconstruction. My current position allows me to bring my various interests together. My research has two strands: uncovering how linguistic knowledge (especially of phonology and morphology) can contribute to natural language processing and using computational models to uncover linguistic knowledge and investigate linguistic hypotheses.
I am currently developing a course on computational models of language below the level of the word.
For more about me, see my curriculum vitae.
Along with Lori Levin, I lead LLab, the LTI linguistics lab.
news
Mar 13, 2024 | My PhD student Brendon Boldt’s paper “ XferBench: a Data-Driven Benchmark for Emergent Language” was accepted to NAACL 2024. |
Mar 13, 2024 | Invited talk at University of Zürich. |
Mar 7, 2024 | Invited talk at ETH Zürich. |
Feb 20, 2024 | Members of our lab, in collaboration with colleagues at ETH Zurich, LMU Munich, JHU, and University of Stuttgart had five papers accepted to LREC-Coling 2024: “Verbing Weirds Language (Models),” “Improved Neural Protoform Reconstruction via Reflex Prediction,” “PWESUITE: Phonetic Word Embeddings and Tasks They Facilitate,” “Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons,” and “Phonotactic Complexity across Dialects.” |
Feb 1, 2024 | My student Brendon Boldt and I have published a substantial article entitled “A Review of the Applications of Deep Learning-Based Emergent Communication,” in TMLR. |