skip to content

Home

Faculty of Modern and Medieval Languages and Linguistics

 

Dr Mohammad Taher Pilehvar

Photo of Taher
Position(s): 
Research Associate, Phenebank
Department/Section: 
Theoretical and Applied Linguistics
Faculty of Modern & Medieval Languages
Contact details: 
Location: 

Department of Theoretical and Applied Linguistics
English Faculty Building
University of Cambridge
9 West Road
Cambridge
CB3 9DP
United Kingdom

About: 

Taher completed his PhD in 2015 under the supervision of Prof. Roberto Navigli in the Sapienza Univeristy of Rome. Taher’s research lies in lexical semantics, mainly focusing on semantic representation, semantic similarity, ontology construction and enrichment, and Word Sense Disambiguation. 

Research interests: 

Natural Language Processing
Lexical semantics
Semantic representation
Word Sense Disambiguation
Machine Translation

Recent research projects: 

MultiJEDI, a 5-year ERC Starting Grant (2011-2016) headed by Prof. Roberto Navigli at the Linguistic Computing Laboratory of the Sapienza University of Rome. 

Published works: 

M. T. Pilehvar and R. Navigli. From Senses to Texts: An All-in-one Graph-based Approach for Measuring Semantic Similarity. Artificial Intelligence, 228, pp. 95-128, Elsevier, 2015.

D. Jurgens, M. T. Pilehvar, and R. Navigli. Cross Level Semantic Similarity: A Evaluation Framework for Universal Measures of Similarity. Language Resources and Evaluation, 43(2), Springer, 2015. 

M. T. Pilehvar and R. Navigli. A Large-scale Pseudoword-based Evaluation Framework for State-of-the-Art Word Sense Disambiguation. Computational Linguistics, 40(4), pp. 837-881, MIT Press, 2014. 

I. Iacobacci, M. T. Pilehvar and R. Navigli. SensEmbed: Learning Sense Embeddings for Word and Relational Similarity. ACL 2015, Beijing, China, 26-31 July 2015, pp. 95-105.

J. Camacho-Collados, M. T. Pilehvar and R. Navigli . A Unified Multilingual Semantic Representation of Concepts. ACL 2015, Beijing, China, 26-31 July 2015, pp. 741-751.

J. Camacho-Collados, M. T. Pilehvar and R. Navigli . A Framework for the Construction of Monolingual and Cross-lingual Semantic Similarity Datasets. ACL 2015, Beijing, China, 26-31 July 2015, pp. 1-7.

J. Camacho-Collados, M. T. Pilehvar and R. Navigli . NASARI: a Novel Approach to a Semantically-Aware Representation of Items. NAACL 2015, Denver, Colorado (US), 31 May-5 June 2015, pp. 567-577. 

M. T. Pilehvar and R. Navigli . An Open-source Framework for Multi-level Semantic Similarity Measurement. NAACL 2015, Denver, Colorado (US), 31 May-5 June 2015, pp. 76-80.

M. T. Pilehvar and R. Navigli. A Robust Approach to Aligning Heterogeneous Lexical Resources. ACL 2014, Baltimore, USA, June 22-27, 2014, pp. 468-478.

D. Jurgens, M. T. Pilehvar, R. Navigli. SemEval-2014 Task 3: Cross-Level Semantic Similarity. COLING 2014, Dublin, Ireland, August 23-24th, 2014, pp. 17-26. 

M. T. Pilehvar, D. Jurgens and R. Navigli. Align, Disambiguate and Walk: A Unified Approach for Measuring Semantic Similarity. ACL 2013, Sofia, Bulgaria, August 4-9, 2013, pp. 1341-1351. Nominated for ACL 2013 best paper award!

M. T. Pilehvar and R. Navigli. Paving the Way to a Large-scale Pseudosense-annotated Dataset. NAACL 2013, Atlanta, USA, June 10-12, 2013, pp. 1100-1109.