Majid Yazdani Home Page

I am a scientist in Artificial Intelligence. My common tools are algorithmic and statistical machine learning. My approach in studying intelligence is not fundamentally different than the approach of a physicist in modeling aerodynamics. When you understand aerodynamics, harnessing nature to build (faster) airplanes is very tempting. Similarly, I find quite often the itch of building novel intelligent systems.



email: myFirstName.yazdaani@gmail.com

Linkedin

Time Line


  • I graduated with my BSc in Computer Engineering from Sharif University of Technology in 2008

  • I worked from December 2008 till September 2013 in Idiap Research Institute.

  • I defended my Ph.D. in June 2013 in Swiss Federal Institute of Technology (EPFL) (link).

  • I worked from October 2013 till December 2015 as a postdoctoral researcher with Jamie Henderson.

  • I was a staff scientist from March 2016 till December 2017 in Linkedin.

  • I work currently at Facebook AI, trying to build neural networks with compartmentalized knowledge and reasoning


Publication (outdated)

  • Majid Yazdani, James Henderson. A Model of Zero-Shot Learning of Spoken Language Understanding , EMNLP 2015.

  • Majid Yazdani, Meghdad Farahmand, James Henderson. Learning Semantic Composition to Detect Non-compositionality of Multiword Expressions, EMNLP 2015.

  • Majid Yazdani, James Henderson. Incremental Recurrent Neural Network Dependency Parser with Search-based Discriminative Training, CoNLL 2015.

  • Helen Hastie, Marie-aude Aufaure, Panos Alexopoulos, Hugues Bouchard,Heriberto Cuayahuitl, Nina Dethlefs, Milica Gasic, James Henderson,Oliver Lemon, Xingkun Liu, Peter Mika, Nesrine Ben Mustapha, Tim Potter, Verena Rieser, Blaise Thomson, Pirros Tsiakoulis, YvesVanrompay, Boris Villazon-Terrazas, Majid Yazdani, Steve Young and Yanchao Yu. The PARLANCE mobile app for interactive search in English and Mandarin, SIGDIAL 2014

  • Hassan Ghasemzadeh Mohammadi, Pierre-Emmanuel Gaillardon, Majid Yazdani, Giovanni De Micheli. Fast Process Variation Analysis in Nano-Scaled Technologies Using Column-Wise Sparse Parameter Selection, IEEE ACM international symposium on nanoscale architectures, 2014.

  • Hassan Ghasemzadeh Mohammadi, Pierre-Emmanuel Gaillardon, Majid Yazdani, Giovanni De Micheli. A Fast TCAD-based Methodology for Variation Analysis of Emerging Nano-Devices, IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, 2013.

  • Majid Yazdani, Ronan Collobert, Andrei Popescu-Belis. Learning to Rank on Network Data, Mining and Learning with Graphs, 2013.

  • Majid Yazdani and Andrei Popescu-Belis. Computing text semantic relatedness using the contents and links of a hypertext encyclopedia, IJCAI, 2013.

  • Majid Yazdani and Andrei Popescu-Belis. Computing text semantic relatedness using the contents and links of a hypertext encyclopedia, Artificial Intelligence Journal 194, 2013, 176–202.

  • Majid Yazdani and Andrei Popescu-Belis. Using a wikipedia-based semantic relatedness measure for document clustering, TextGraphs-6: Graph-based Methods for Natural Language Processing, 2011.

  • Andrei Popescu-Belis, Majid Yazdani, Alexandre Nanchen, and Philip N. Garner. A speech-based just-in-time retrieval system using semantic search, ACL Systems Demonstrations, 2011.

  • Andrei Popescu-Belis, Majid Yazdani, Alexandre Nanchen, and Philip N. Garner. A just-in-time document retrieval system for dialogues or monologues, SIGDIAL, 2011.

  • Majid Yazdani and Andrei Popescu-Belis. A random walk framework to compute textual semantic similarity: A unified model for three benchmark tasks, ICSC , 2010.

  • Majid Yazdani, Milad Eftekhar, and Hassan Abolhassani. Tree-based method for classifying websites using extended hidden markov models, PAKDD , 09.