Label-Efficient Model Selection for Text Generation
- Shir Ashury Tahan
- Ariel Gera
- et al.
- 2024
- ACL 2024
I am a Senior Research Scientist at IBM Israel Research Lab, managing the Language & Retrieval group.
I joined IBM Research to be part of Project Debater, the first AI system that can debate humans on complex topics, as responsible for its NLP pipeline and tools. Later became a team lead working on Argument Mining, Argument Quality, Weak Supervision, and Debate Rebuttal.
I am leading Label Sleuth an open-source no-code system for text labeling and text classifiers building with no AI nor programing knowledge needed - from unlabeled data to a working classifier in just a few hours!
I received my Ph.D. in Computer Science from Bar Ilan University, where I have worked on semantic inference under the supervision of Prof. Ido Dagan and Prof. Jacob Goldberger. There I developed algorithms for the acquisition of lexical semantic relations, proposed methods for the integration of knowledge resources and built probabilistic models for inference at the lexical level.
Program Committee:
IBM Cognitive computing colloquium - November 2014
Israeli Seminar on Computational Linguistics (ISCOL) - September 2014
Israeli Seminar on Computational Linguistics (ISCOL) - October2018