Papers by Omer Shubi

4 papers
Déjà Vu? Decoding Repeated Reading from Eye Movements (2025.acl-long)

Copied to clipboard

Challenge: In many daily situations we read the same text more than once.
Approach: They propose a strategy for enhancing feature-based and neural models by generating machine generated eye movements from a cognitive model.
Outcome: The proposed model improves on the previous model and enables better characterization of the role of memory in repeated reading.
Fine-Grained Prediction of Reading Comprehension from Eye Movements (2024.emnlp-main)

Copied to clipboard

Challenge: a new study attempts to assess reading comprehension from eye movements in reading . eye movements provide small improvements over a text-only baseline, the authors argue .
Approach: They propose to use eyetracking data to predict reading comprehension of a single participant . they use a battery of recent models and three new multimodal language models .
Outcome: The proposed model can predict reading comprehension of a single participant from eye movements over a paragraph.
Eye Tracking and NLP (2025.acl-tutorials)

Copied to clipboard

Challenge: tutorial combines eye tracking during reading with NLP . outlines how eye movements in reading can be leveraged for NLP methods .
Approach: The tutorial combines eye tracking during reading with NLP . it covers eye movements in reading, integrating eye movement data in NLP models .
Outcome: The tutorial outlines how eye movements in reading can be leveraged for NLP . it provides the essential background for conducting research on joint modeling of eye movements and text.
Decoding Reading Goals from Eye Movements (2025.acl-long)

Copied to clipboard

Challenge: a study examines whether readers can distinguish between two types of reading goals: information seeking and ordinary reading for comprehension.
Approach: They propose a method to distinguish between two types of reading goals: information seeking and ordinary reading for comprehension.
Outcome: The proposed model solves the reading goal-oriented task with the most accurate predictions in real time, the authors say .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations