HomeResearchProjectsResumeCodeNotes


Seth Ebner

seth@cs.jhu.edu

Hello, World!

I'm Seth Ebner, a fifth-year PhD student at Johns Hopkins University affiliated with the Center for Language and Speech Processing. My advisor is Benjamin Van Durme.

Research interests

I am interested in natural language processing and computational linguistics, particularly semantics and pragmatics and their applications. Most of my recent work has focused on information extraction, especially in multi-sentence and multilingual or cross-lingual settings. I also work on representations and models of speaker belief.

I have also done research in text-to-speech processing, neuromorphic architectures, binary integer programming, and cache replacement policies.

Selected publications

Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction. EMNLP 2021. M. Yarmohammadi, S. Wu, M. Marone, H. Xu, S. Ebner, G. Qin, Y. Chen, J. Guo, C. Harman, K. Murray, A. S. White, M. Dredze, B. Van Durme. [paper]

Gradual Fine-Tuning for Low-Resource Domain Adaptation. Domain Adaptation for NLP 2021. H. Xu, S. Ebner, M. Yarmohammadi, A. S. White, B. Van Durme, K. Murray. [paper] [poster]

Multi-Sentence Argument Linking. ACL 2020. S. Ebner*, P. Xia*, R. Culkin, K. Rawlins, B. Van Durme. [paper] [code] [slides]

Reading the Manual: Event Extraction as Definition Comprehension. Structured Prediction for NLP 2020. Y. Chen, T. Chen, S. Ebner, B. Van Durme. [paper]

Bag-of-Words Transfer: Non-Contextual Techniques for Multi-Task Learning. DeepLo 2019. S. Ebner, F. Wang, B. Van Durme. [paper] [code] [poster]

An Exact No Free Lunch Theorem for Community Detection. COMPLEX NETWORKS 2019. A. D. McCarthy, T. Chen, S. Ebner. [paper]

Additional writings

Intension in Literature. 2018. [paper]

An Analysis of Metareference. 2017. [paper]

Semantic Relatedness through Ontologies and Wikipedia. 2017. [paper]


I have written a LaTeX linter for catching common mistakes (especially concerning citations and references to document elements) in LaTeX documents.
Run the linter with: python latexlint.py --dir /path/to/latexfiles <flags> (requires Python 3.6 or later). Flags are set to False by default.
To see the full list of flags, run: python latexlint.py -h