My main areas of interest are Artificial intelligence (AI), Machine Learning (ML), and Natural Language Processing (NLP). My current research focuses on providing an analytical framework for understanding how individuals make various decisions on social media, including spread of mis/disinformation. I am also interested in Commonsense Reasoning and Story Understanding in natural language. I work on developing NLP models to extract causal relations, explicit or implicit, in discourse. My goal is to leverage these models in enabling machines to better understand stories and find causal chains among events in a story.
News & updates
- GisPy Code Our paper GisPy: A Tool for Measuring Gist Inference Score in Text is accepted to the 4th Workshop on Narrative Understanding @ NAACL 2022.
- Code+Data Our paper Knowledge-Augmented Language Models for Cause-Effect Relation Classification is accepted to the Commonsense Representation and Reasoning (CSRR) @ ACL 2022.
- Code+Data Our paper ParsiNLU: A Suite of Language Understanding Challenges for Persian, the result of a great collaborative work, is accepted to the Transactions of the Association for Computational Linguistics (TACL), 2021 and will be presented at EMNLP 2021.
- I received the Linguistics Data Consortium’s (LDC) Fall 2020 Data Scholarship for my research in automatic detection of causal relations in text.
- I received the award for Best CS Graduate Research at Annual R&D Showcase at School of Engineering (SEAS) at the George Washington University (GWU).
- We received the Social Media and Democracy Research Grant from The Social Science Research Council (SSRC) for our project on “Identifying Best Practices to Correct Misinformation on Facebook”.