Ben Bogin

PhD Student, Computer Science

Tel Aviv University

Hi! I’m a PhD student in Tel Aviv University, advised by Jonathan Berant. My main research interest is Natural Language Processing. I am mostly interested in semantic parsing and models that try to understand grounded, compositional communication.



Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering (TACL, 2020).
Obtaining Faithful Interpretations from Compositional Neural Networks (ACL, 2020).
Evaluating nlp models via contrast sets (Findings of EMNLP, 2020).
Global Reasoning over Database Structures for Text-to-SQL Parsing (EMNLP, 2019).
Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing (ACL, 2019).
Grammar-based Neural Text-to-SQL Generation (2019).
Emergence of Communication in an Interactive World with Consistent Speakers (Emergent Communication Workshop at NIPS, 2018).
Towards an argumentative content search engine using weak supervision (COLING, 2018).
Language Generation with Recurrent Generative Adversarial Networks without Pre-training (Subword and Character level models in NLP Workshop, EMNLP, 2017).