Mohaddeseh Bastan

mbastan[AT]cs[DOT]stonybrook[DOT]edu

I am a PhD candidate in Department of Computer Science at Stony Brook University and also a member of Institute for AI-Driven Discovery and Innovation. I am fortunately advised by Dr. Niranjan Balasubramanian. I'm working on different applicatioins of natural language processing including but not limited to sentiment analysis, machinne translation, explanation generation, and text summarization. My goal is to make deep learning models generate and explain the reason behind their decisions in human language. Before joining SBU I obtained my B.Sc and M.Sc. degrees in the department of Computer Engineering at Amirkabir University of Technology in Tehran, Iran.

Education

State University of New York at Stony Brook

PhD in Computer Science
Thesis: Making Neural Network Models Perspicuous by Generating Explanation
August 2017 - May 2023

Amirkabir University of Technology

MSc in Computer Engineering-Artificial Intelligence
Thesis: English to Persian Translation Using Deep Recurrent Neural Networks
Supervisor: Shahram Khadivi
August 2014 - Jan 2017

Amirkabir University of Technology

BSc in Computer Engineering-Software Engineering
Thesis: Design and Implementation of a Translator and Summarizer System
Supervisor: Shahram Khadivi
August 2010 - August 2014

Experiences

Microsoft

Data Science Intern
Working in Machine Translation team on improving live data translation with unsupervised methods.
Supervisor: Vishal Chowdhary
June 2021 - August 2021

Microsoft

Data Science Intern
Working in Text Analytics team on improving the quality of the summarized text using correction methods based on the source input.
Supervisors: Benjamin Han and Chenguang Zhu
June 2020 - August 2020

Stony Brook University

Research Assistant
Working on different NLP applications, more specifically making neural networks explanable in human language.
August 2017 - Now

Publications

BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples

Mohaddeseh Bastan, Mihai Surdeanu, Niranjan Balasubramanian

Findings of the Association for Computational Linguistics: EMNLP 2022

[PDF] [Project Page] [Presentation]

A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings

Mohaddeseh Bastan, Shahram Khadivi

In Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022) @COLING

[PDF]

SuMe: A Dataset Towards Summarizing Biomedical Mechanisms

Mohaddeseh Bastan, Nishant Shankar, Mihai Surdeanu, Niranjan Balasubramanian

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022)

[PDF] [Code] [Project Page]

Author’s Sentiment Prediction

Mohaddeseh Bastan, Mahnaz Koupaee, Youngseo Son, Richard Sicoli, Niranjan Balasubramanian

Proceedings of the 28th International Conference on Computational Linguistics, 2020

[PDF] [Code] [Project Page] [Presentation]

Modeling Label Semantics for Predicting Emotional Reactions

Radhika Gaonkar, Heeyoung Kwon, Mohaddeseh Bastan, Niranjan Balasubramanian, Nathanael Chambers

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020

[PDF] [Code]

Neural machine translation on scarce-resource condition: a case-study on Persian-English

Mohaddeseh Bastan, Shahram Khadivi, Mohammad Mehdi Homayounpour

2017 Iranian Conference on Electrical Engineering (ICEE), 2017

[PDF]

Monolingually Derived Phrase Scores for Phrase Based SMT Using Neural Networks Vector Representations

Amir Pouya Aghasadeghi, Mohadeseh Bastan

arXiv, 2015

[PDF]

Skills

Programming Languages
Machine Learning Tools
  • Tensorflow
  • PyTorch
  • Blocks
  • Theano

Honors & Awards

  • Awarded scholarship to attend ICLR, 2022 from WiML organizition
  • Awarded full scholarship to attend Grad Cohort Workshop, 2020
  • Awarded full scholarship to attend Grad Cohort Workshop, 2019
  • Awarded an Excellence as a TA, Stony Brook University, 2018-2019
  • Awarded the travel grant to attend ICLR conference, 2019
  • Awarded the travel grant to attend ICML conference, 2019
  • Granted Merit Fellowship for 3 years, Stony Brook University, 2017-2020
  • Granted admission from Talented Students Office of Amirkabir University of Technology to study at Graduate level without the entrance exam, 2014

Interests

I enjoy nature. During the warmer months here, I like to walk in the countryside and outdoors. I'm a professional swimmer and If time allows, I go for swimming. I'm also an aspiring chef. When forced indoors, I try a new recipe because I like learning something new. I spend a large amount of my free time exploring the latest technology advancements in the AI world.