Projects per year
Personal profile
Biography
Hello! I am an assistant professor in the Department of Data Science and Artificial Intelligence of Monash, and an affiliated lecturer of University of Cambridge. Prior to joining Monash, I was a lecturer at the Department of Electrical and Electronic Engineering of UCL, and before that a postdoc in the Language Technology Lab at University of Cambridge.
I lead a team of students working on predictive models for language (text and speech). During my PhD I worked on integrating nonparametric models and compressed data structures for predictive models on large volumes of text. In my PostDoc, I worked on multilingual NLP and Bayesian learning of neural models with their application in low-resource conditions. Since 2019 I have been working on various speech and text models in understanding, translation, and reasoning tasks. While in principle the solutions we investigate are agnostic to the underlying models, we leverage foundational large language models (for text and speech) as much as possible. Hence, in recent years my team has also been investigating various shortcomings of such models.
Research interests
- Probing and Augmenting LLMs (verification, symbolic grounding)
- Self-supervised learning (e.g., applications in text, speech, and graph)
- Utilising graphs for knowledge intensive tasks (e.g., graph-to-text generation, applications in biomedical domain)
- Deep generative models (e.g., generation, semi-supervised learning, sparsity and disentanglement)
- Bayesian learning and inference (e.g., applications in training with small data)
Monash teaching commitment
Ehsan has experience as both the Chief Examiner and Lecturer for the following units in the Faculty of IT:
- FIT5217 Natural Language Processing
- FIT5212 Data Analysis for Semi-structured Data
University Service
- Early Career Academic (ECA) Committee (2022-2023)
Community service
Program Committee
- Association of Computational Linguistics (ACL)
- North American Chapter of Association of Computational Linguistics (NAACL)
- Empirical Methods in Natural Language Processing (EMNLP)
- Association for the Advancement of Artificial Intelligence (AAAI)
- The International Joint Conference on Artificial Intelligence (IJCAI)
Expertise related to UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This person’s work contributes towards the following SDG(s):
Education/Academic qualification
Computer Science, PhD, Scalable Non-Markovian Sequential Modelling for Natural Language Processing, MONASH UNIVERSITY
Award Date: 18 Oct 2017
Computer Science, BSc, Text summarization with harmony search algorithm, Shahid Beheshti University
Award Date: 1 Sept 2009
External positions
Affiliated Lecturer, University of Cambridge
1 Oct 2020 → 30 Sept 2024
Research area keywords
- Natural Language Processing
- Large Language Models
- Deep Generative Models
Collaborations and top research areas from the last five years
Projects
- 1 Finished
-
Paul Ramsay Foundation: Tracking media and parliamentary narratives around cycles of disadvantage in Australia
Webb, G., Angus, S., Goodwin, S., Dwyer, T., Smith, L., Bragge, P., Batstone, J. & Shareghi Nojehdeh, E.
29/09/22 → 30/08/23
Project: Research
-
Generating synthetic speech from SpokenVocab for speech translation
Zhao, J., Haffari, G. & Shareghi, E., 2023, EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023. Cotterell, R. & Scarton, C. (eds.). Stroudsburg PA USA: Association for Computational Linguistics (ACL), p. 1975–1981 7 p.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
Open AccessFile -
Investigating pre-trained audio encoders in the low-resource condition
Yang, H., Zhao, J., Haffari, R. & Shareghi, E., 2023, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2023. Harte, N., Berndsen, J. & Jones, G. (eds.). Dublin Ireland: International Speech Communication Association (ISCA), p. 1498-1502 5 p.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
Open AccessFile -
Fire burns, sword cuts: commonsense inductive bias for exploration in text-based games
Ryu, D. K., Shareghi, E., Fang, M., Xu, Y., Pan, S. & Haffari, R., 2022, ACL 2022, The 60th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 2 (Short Papers). Croce, D., Cotterell, R. & Zhang, J. (eds.). Stroudsburg PA USA: Association for Computational Linguistics (ACL), p. 515–522 8 p. (Proceedings of the Annual Meeting of the Association for Computational Linguistics; vol. 2).Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
Open AccessFile4 Citations (Scopus) -
Introduction
Cherry, C., Fan, A., Foster, G., Haffari, R., Khadivi, S., Peng, N., Ren, X., Shareghi, E. & Swayamdipta, S., 2022, The 3rdWorkshop on Deep Learning Approaches for Low-Resource NLP, Proceedings of the DeepLoWorkshop. Cherry, C., Fan, A., Foster, G., Haffari, G., Khadivi, S., Peng, N., Ren, X., Shareghi, E. & Swayamdipta, S. (eds.). Stroudsburg PA USA: Association for Computational Linguistics (ACL), p. iv 1 p.Research output: Chapter in Book/Report/Conference proceeding › Foreword / Postscript › Other
Open AccessFile -
M-Adapter: modality adaptation for end-to-end speech-to-text translation
Zhao, J., Yang, H., Shareghi, E. & Haffari, G., 2022, Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2022. Lee, K., Lamel, L., Hasegawa-Johnson, M., Livescu, K. & Kang, O. (eds.). France: International Speech Communication Association (ISCA), p. 111-115 5 p.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
Open AccessFile3 Citations (Scopus)