Till startsida
University of Gothenburg
Sitemap
To content Read more about how we use cookies on gu.se

Mohammad Mehdi Ghanimifard

Doctoral student

Mohammad Mehdi Ghanimifard
Doctoral student
Computational Linguistics
mehdi.ghanimifard@gu.se
+46 31 786 4038

Room number: 113
Postal Address: Box 200, 40530 Göteborg
Visiting Address: Dicksonsgatan 4 , 41256 Göteborg


Linguistics, Logic and Theory of Science unit at Department of Philosophy, Linguistics, Theory of Science (More Information)
Box 200
405 30 Göteborg
www.flov.gu.se
flov@flov.gu.se
Visiting Address: Olof Wijksgatan 6 , 412 55 Göteborg

About Mohammad Mehdi Ghanimifard

I am PhD candidate in Computational Linguistics. My research area is in modelling language understanding and generation with grounded neural language models. I am interested in examining models which can combine linguistic representations and uncertain perceptual representations in a single framework.

I think composition/fusion of different types of information is the core problem for understanding. In a sense, understanding by nature is about changing several representations and map them in computable representations. When we generalise from compositional evidence, the meaningful and non-symbolic representations (e.g. sensory representations) must be composed into abstract and complex representation (e.g. concepts, type of objects etc.).

Modelling language essentially deals with high level representations. For example, neural language models parameterise representations. As a computational matter, neural networks provide scalable building blocks which can use recent hardwares for processing large amount of data. The most successful areas for these models are in vision and speech.

When we deal with grounded language in visual perception, several different levels of representations for both vision and language models is required. Explaining where and when we need composition and fusion of different representations will guide us toward robust models for vision and language. In this sense, my research is about modelling language and vision compositionality with parametric representations in neural networks.

In addition to my research as PhD student, I have been TA for following courses in Master in Language Technology programme in last three years:

  • Artificial intelligence: Cognitive systems (Formerly: "Embodied and Situated Language Processing") (November-January)
  • Statistical Methods for NLP (January to March)
  • Computational Semantics (April-June)

 

Latest publications

Visual grounding of spatial relations in recurrent neural language models
Mehdi Ghanimifard, Simon Dobnik
Workshop on Models and Representations in Spatial Cognition (MRSC-3) at 11th International Conference on Spatial Cognition 2018, 5 September 2018, Tübingen, Germany, Conference contribution 2018
Conference contribution

Exploring the Functional and Geometric Bias of Spatial Relations Using Neural Language Models
Simon Dobnik, Mehdi Ghanimifard, John D. Kelleher
Proceedings of SpLU 2018 at NAACL-HLT 2018, June 6, 2018 New Orleans, Louisiana / Parisa Kordjamshidi, Archna Bhatia, James Pustejovsky, Marie-Francine Moens (eds.) , New Orleans, Louisiana, USA, Association of Computational Linguistics (ACL), Conference paper 2018
Conference paper

Bigrams and BiLSTMs Two neural networks for sequential metaphor detection
Yuri Bizzoni, Mehdi Ghanimifard
NAACL HLT 2018. Proceedings of the Workshop Figurative Language Processing. 6 June 2018 New Orleans, Louisiana, New Orleans, Louisiana, USA, Association of Computational Linguistics (ACL), Conference paper 2018
Conference paper

Learning to Compose Spatial Relations with Grounded Neural Language Models
Mehdi Ghanimifard, Simon Dobnik
Proceedings of IWCS 2017: 12th International Conference on Computational Semantics, Montpellier 19-22 September 2017 / Claire Gardent and Christian Retoré (eds.), Association for Computational Linguistics, Conference paper 2017
Conference paper

"Deep" Learning : Detecting Metaphoricity in Adjective-Noun Pairs
Yuri Bizzoni, Stergios Chatzikyriakidis, Mehdi Ghanimifard
Proceedings of the Workshop on Stylistic Variation, EMNLP2017, ACL, Conference paper 2017
Conference paper

Learning to compose spatial relations with grounded neural language models
Mehdi Ghanimifard, Simon Dobnik
Second International Workshop on Models and Representations in Spatial Cognition (MRSC). Schloss Hohentübingen; Tübingen, Germany; April 06 - 07, 2017, Poster 2017
Poster

Compositionality for Classifiers
Staffan Larsson, Mehdi Ghanimifard, Simon Dobnik
Johanna Björklund, Sara Stymne: SLTC 2016, Conference paper 2016
Conference paper

Enriching Word-sense Embeddings with Translational Context
Mehdi Ghanimifard, Richard Johansson
Proceedings of Recent Advances in Natural Language Processing / edited by Galia Angelova, Kalina Bontcheva, Ruslan Mitkov. International Conference, Hissar, Bulgaria 7–9 September, 2015, Conference paper 2015
Conference paper

Showing 1 - 8 of 8

2018

Visual grounding of spatial relations in recurrent neural language models
Mehdi Ghanimifard, Simon Dobnik
Workshop on Models and Representations in Spatial Cognition (MRSC-3) at 11th International Conference on Spatial Cognition 2018, 5 September 2018, Tübingen, Germany, Conference contribution 2018
Conference contribution

Exploring the Functional and Geometric Bias of Spatial Relations Using Neural Language Models
Simon Dobnik, Mehdi Ghanimifard, John D. Kelleher
Proceedings of SpLU 2018 at NAACL-HLT 2018, June 6, 2018 New Orleans, Louisiana / Parisa Kordjamshidi, Archna Bhatia, James Pustejovsky, Marie-Francine Moens (eds.) , New Orleans, Louisiana, USA, Association of Computational Linguistics (ACL), Conference paper 2018
Conference paper

Bigrams and BiLSTMs Two neural networks for sequential metaphor detection
Yuri Bizzoni, Mehdi Ghanimifard
NAACL HLT 2018. Proceedings of the Workshop Figurative Language Processing. 6 June 2018 New Orleans, Louisiana, New Orleans, Louisiana, USA, Association of Computational Linguistics (ACL), Conference paper 2018
Conference paper

2017

Learning to Compose Spatial Relations with Grounded Neural Language Models
Mehdi Ghanimifard, Simon Dobnik
Proceedings of IWCS 2017: 12th International Conference on Computational Semantics, Montpellier 19-22 September 2017 / Claire Gardent and Christian Retoré (eds.), Association for Computational Linguistics, Conference paper 2017
Conference paper

"Deep" Learning : Detecting Metaphoricity in Adjective-Noun Pairs
Yuri Bizzoni, Stergios Chatzikyriakidis, Mehdi Ghanimifard
Proceedings of the Workshop on Stylistic Variation, EMNLP2017, ACL, Conference paper 2017
Conference paper

Learning to compose spatial relations with grounded neural language models
Mehdi Ghanimifard, Simon Dobnik
Second International Workshop on Models and Representations in Spatial Cognition (MRSC). Schloss Hohentübingen; Tübingen, Germany; April 06 - 07, 2017, Poster 2017
Poster

2016

Compositionality for Classifiers
Staffan Larsson, Mehdi Ghanimifard, Simon Dobnik
Johanna Björklund, Sara Stymne: SLTC 2016, Conference paper 2016
Conference paper

2015

Enriching Word-sense Embeddings with Translational Context
Mehdi Ghanimifard, Richard Johansson
Proceedings of Recent Advances in Natural Language Processing / edited by Galia Angelova, Kalina Bontcheva, Ruslan Mitkov. International Conference, Hissar, Bulgaria 7–9 September, 2015, Conference paper 2015
Conference paper

Showing 1 - 8 of 8

Page Manager: Webbredaktionen|Last update: 5/4/2016
Share:

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?