Bootstrapping Small & High Performance Language Models with Unmasking-Removal Training Policy.
Yahan Yang , Elior Sulem, Insup Lee, and Dan Roth,
EMNLP 2023 [Paper: pdf]
Penn & BGU BabyBERTa+ for Strict-Small BabyLM Challenge
Yahan Yang , Elior Sulem, Insup Lee, and Dan Roth,
BabyLM Challenge 2023 [Paper: pdf]
Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey.
Bonan Min*, Hayley Ross*, Elior Sulem*, Amir Pouran Ben Veyseh*, Thien Huu Nguyen, Oscar Sainz, Eneko Agirre, Ilana Heinz, and Dan Roth, *Equal contribution
ACM Computing Surveys, 2023 [ArXiv Version: pdf] [Paper: link]
Capturing the Content of a Document through Complex Event Identification.
Zheng Qi , Elior Sulem, Haoyu Wang, Xiaodong Yu, and Dan Roth,
*SEM 2022
[Paper: pdf][Code: github][Slides: pdf][Video: link]
Yes, No or IDK: The Challenge of Unanswerable Yes/No Questions.
Elior Sulem, Jamaal Hay, and Dan Roth,
NAACL 2022
[Paper: pdf][Data & Code: github][Slides: pdf][Poster: pdf][Video: link]
BabyBERTa: Learning More Grammar With Small-Scale Child-Directed Language.
Philip Huebner, Elior Sulem, Cynthia Fisher, and Dan Roth,
CoNLL 2021
[Paper: pdf][Data & Code: github][Demo: link][Slides: pdf][Video: link]
Best Paper Award Runner-Up
Do We Know What We Don’t Know? Studying Unanswerable Questions beyond SQuAD 2.0.
Elior Sulem, Jamaal Hay, and Dan Roth,
Findings of EMNLP 2021
[Paper: pdf][Repo: github][Slides: pdf][Poster: pdf][Video: link]
Zero-shot Event Extraction via Transfer Learning: Challenges and Insights.
Qing Lyu , Hongming Zhang, Elior Sulem, and Dan Roth,
ACL 2021
[Paper: pdf][Code: github][Demo: link][Slides: pdf][Video: link]
Semantic Structural Decomposition for Neural Machine Translation.
Elior Sulem, Omri Abend, and Ari Rappoport,
*SEM 2020
[Paper: pdf] [Data & Code: github] [Slides: pdf]
The Language of Legal and Illegal Activity on the Darknet.
Leshem Choshen*, Dan Eldad*, Daniel Hershcovich*, Elior Sulem*, and Omri Abend,
* Equal contribution.
ACL 2019
[Paper: pdf] [Code: github] [Data: upon request]
SemEval 2019 Task 1: Cross-lingual Semantic Parsing with UCCA.
Daniel Hershcovich, Zohar Aizenbud, Leshem Choshen, Elior Sulem, Ari Rappoport, and Omri Abend,
SemEval 2019
[Paper: pdf] [Website: codalab]
BLEU is Not Suitable for the Evaluation of Text Simplification.
Elior Sulem, Omri Abend and Ari Rappoport,
EMNLP 2018
[Paper: pdf] [Supp. Material: pdf] [Data: github] [Poster: pdf]
Simple and Effective Text Simplification Using Semantic and Neural Methods.
Elior Sulem, Omri Abend and Ari Rappoport,
ACL 2018
[Paper: pdf] [Data: github] [Slides: pdf] [Video: link]
Semantic Structural Evaluation for Text Simplification.
Elior Sulem, Omri Abend and Ari Rappoport,
NAACL 2018
[Paper: pdf] [Data & Code: github] [Slides: pdf] [Video: link]
Conceptual Annotations Preserve Structure Across Translations: A French-English Case Study.
Elior Sulem, Omri Abend and Ari Rappoport,
ACL 2015 Workshop on Semantics-Driven Statistical Machine Translation (S2MT)
[Paper: pdf] [Data: link]
Elior Sulem - Homepage 