About

I am an Assistant Professor at Tehran Institute for Advanced Studies (TeIAS) and an Affiliated Lecturer at the University of Cambridge.

My primary research interest lies in the area of Natural Language Processing (NLP) where I have worked on different problems in lexical semantics, such as semantic representation and similarity, sense representation, word sense disambiguation, and ontology construction and alignment.

[google scholar] [twitter]

Background

Iran University of Science and Technology

I was an Assistant Professor at the Computer Engineering department of IUST (2018-2020). During this time, I taught multiple graduate and undergraduate courses (AI, Deep Learning, NLP, and Advanced Programming) and supervised several graduate students.


University of Cambridge

I was a Research Associate at the Language Technology Lab of the University of Cambridge (2015-2018). During this, I worked on PheneBank (PI: Dr. Nigel Collier), a project at the intersection of Natural Language Processing and Biomedical sciences, funded by the UK's Medical Research Council.

Sapienza University

I did my PhD at the Linguistic Computing Laboratory of the Sapienza University of Rome, Italy. My PhD advisor was Dr. Roberto Navigli with whom I did research in lexical semantics with a specific focus on the unified semantic representation of different linguistic items.

News

    Our book on Embeddings in NLP is finally out! Check here for prints and ebooks (more info). An early draft of the book can be obtained from here.

  • Contact me if you are interested in attending undergraduate or graduate NLP study groups.
  • April 2022: Long paper accepted at NAACL 2022: a new token attribution method (called GlobEnc) with significant boost over existing techniques; plus a demo paper on DadmaTools, a new NLP toolkit for Farsi.
  • April 2022: Talk on isotropy of contextualised spaces at the University of Sheffield (remote).
  • March 2022: AdapLeR is out, up to 22x infrence speedup while retaining performance (ACL 2022).
  • Feb 2022: Five papers acccepted in ACL 2022! 3 in the main conference, 2 in the Findings (almost all with my Master's students). Details soon.
  • Jan 2022: To serve as a member of Steering Committee for SemEval-2022, Senior AC for NAACL-2022, Senior PC for AAAI-2022 and IJCAI-ECAI-2022, and PC for *ACL-2022 tutorials.
  • Jan 2022: Contact me if you'd like to audit the graduate NLP course (in Farsi).
  • Dec 2021: Gave a talk on isotropy of contextualised spaces to London Meta Research (remote).
  • Dec 2021: I will be the Program Co-Chair of *SEM-2022, with Ellie Pavlick (Brown University).
  • Oct 2021: Our work on the PheneBank project was accepted for publication at Bioinformatics.
  • Sep 2021: The Word-in-Context dataset has a dedicated subsection in the 3rd edition of Jurafsky&Martin Speech and Language Processing textbook!
  • Sep 2021: EMNLP-2021 papers: Token-level probing of BERT (main), A critical investigation of dataset bias mitigation techniques (Findings), Isotropy of fine-tuned spaces (Findings), A cross-model comparison of BERToid models (BlackboxNLP).

Publications

D. Loureiro, K. Rezaee, M. T. Pilehvar, J. Camacho-Collados
Language Models for Word Sense Disambiguation.
Computational Linguistics 2021.

A. Breit, A. Revenko, K. Rezaee, M. T. Pilehvar, J. Camacho-Collados
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context
EACL 2021.

C. Conforti, J. Berndt, M. T. Pilehvar, C. Giannitsarou, F. Toxvaerd, and N. Collier
STANDER: An Expert-Annotated Dataset for News Stance Detection and Evidence Retrieval.
Findings of EMNLP 2020.

A. Raganato, T. Pasini, J. Camacho-Collados, and M.T. Pilehvar
XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization.
EMNLP 2020.

C. Conforti, J. Berndt, M. T. Pilehvar, C. Giannitsarou, F. Toxvaerd, and N. Collier
Will-They-Won't-They: A Very Large Dataset for Stance Detection on Twitter.
ACL 2020.

M Gritta, MT Pilehvar, and N Collier
A pragmatic guide to geoparsing evaluation.
Language Resources and Evaluation, 2020.

V. Prokhorov, M. T. Pilehvar, D. Kartsaklis, P. Lio, and N. Collier
Unseen Word Representation by Aligning Heterogeneous Lexical Semantic Spaces.
AAAI 2019, Hawaii, USA.

M. T. Pilehvar and J. Camacho-Collados
WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations.
NAACL 2019, Minneapolis, USA.


M. T. Pilehvar
On the Importance of Distinguishing Word Meaning Representations: A Case Study on Reverse Dictionary Mapping.
NAACL 2019, Minneapolis, USA.

V. Prokhorov, M. T. Pilehvar, and N. Collier
Generating Knowledge Graph Paths from Textual Definitions using Sequence-to-Sequence Models.
NAACL 2019, Minneapolis, USA.

Teachings

Artificial Intelligence (undergraduate)

I have taught this course several times at IUST: [spring 97][fall 97][fall 98][spring 99][fall 99]


Deep Learning (graduate)

My deep learning courses are mostly applied, with special focus on working with deep learning frameworks, such as Keras, Tensorflow, and Pytorch. [fall 97][fall 98][fall 99]


Deep Learning (undergraduate)

I usually dedicate the last few weeks of the undergraduate AI course to teaching basics of deep learning. However, due to high interest, I once tried having a full undergraduate course on deep learning in [spring 98].


Natural Language Processing (graduate)

I'm currently teaching a graduate course on the topic (for the first time). Please feel free to join!


Advanced Programming (undergraduate)

My Java programming course in [fall 97].

Other

I enjoy stargazing laying flat on my back outside under the clear skies of my hometown (Hamedan). Many years ago, when I was younger, I used to do some astrophotography. I used to send my photos to Spaceweather.com. I think this is my last photo published on Spaceweather. I once had a photo published in Astronomy Magazine (the largest U.S. magazine on the subject).



Contact

  • mp792@cam.ac.uk

Department of Theoretical and Applied Linguistics
University of Cambridge
Sidgwick Avenue
Cambridge
CB3 9DA
United Kingdom