Log In Sign Up

TorontoCL at CMCL 2021 Shared Task: RoBERTa with Multi-Stage Fine-Tuning for Eye-Tracking Prediction

by   Bai Li, et al.

Eye movement data during reading is a useful source of information for understanding language comprehension processes. In this paper, we describe our submission to the CMCL 2021 shared task on predicting human reading patterns. Our model uses RoBERTa with a regression layer to predict 5 eye-tracking features. We train the model in two stages: we first fine-tune on the Provo corpus (another eye-tracking dataset), then fine-tune on the task data. We compare different Transformer models and apply ensembling methods to improve the performance. Our final submission achieves a MAE score of 3.929, ranking 3rd place out of 13 teams that participated in this shared task.


page 1

page 2

page 3

page 4


Zero Shot Crosslingual Eye-Tracking Data Prediction using Multilingual Transformer Models

Eye tracking data during reading is a useful source of information to un...

LAST at CMCL 2021 Shared Task: Predicting Gaze Data During Reading with a Gradient Boosting Decision Tree Approach

A LightGBM model fed with target word lexical characteristics and featur...

Reading Task Classification Using EEG and Eye-Tracking Data

The Zurich Cognitive Language Processing Corpus (ZuCo) provides eye-trac...

Dynamic Graph Modeling of Simultaneous EEG and Eye-tracking Data for Reading Task Identification

We present a new approach, that we call AdaGTCN, for identifying human r...

Leveraging recent advances in Pre-Trained Language Models forEye-Tracking Prediction

Cognitively inspired Natural Language Pro-cessing uses human-derived beh...

Automatic selection of eye tracking variables in visual categorization in adults and infants

Visual categorization and learning of visual categories exhibit early on...