GazeReader: Detecting Unknown Word Using Webcam for English as a Second Language (ESL) Learners.

Automatic unknown word detection techniques can enable new applications for assisting English as a Second Language (ESL) learners, thus improving their reading experiences. However, most modern unknown word detection methods require dedicated eye-tracking devices with high precision that are not easily accessible to end-users. In this work, we propose GazeReader, an unknown word detection method only using a webcam. GazeReader tracks the learner’s gaze and then applies a transformer-based machine learning model that encodes the text information to locate the unknown word. We applied knowledge enhancement including term frequency, part of speech, and named entity recognition to improve the performance. The user study indicates that the accuracy and F1-score of our method were 98.09% and 75.73%, respectively. Lastly, we explored the design scope for ESL reading and discussed the findings.

My contributions:

• Proposed this idea, led this project and wrote most of the paper.
• Built a web-based pdf reader using pdf.js and React to collect users’ gaze data while reading.
• Implemented a transformer-based model to detect unknown words based on gaze and text data. The accuracy is 97.6% and the F1-score is 71.1%, which is higher than the state-of-arts.
• Showed the robustness of our method on less precise webcam-based gaze data with an accuracy of 97.3%.

Download paper here