CogNLP-Sheffield at CMCL 2021 Shared Task: Blending Cognitively Inspired Features with Transformer-based Language Models for Predicting Eye Tracking Patterns.
Peter VickersRosa WainwrightHarish Tayyar MadabushiAline VillavicencioPublished in: CMLS (2021)
Keyphrases
- eye tracking
- language model
- language modeling
- eye movements
- human computer interaction
- n gram
- visual attention
- eye tracking data
- probabilistic model
- speech recognition
- information retrieval
- eye gaze
- query expansion
- gaze estimation
- eye tracker
- test collection
- language modelling
- document retrieval
- low level
- feature extraction
- feature vectors
- feature space
- query terms
- semantic information
- co occurrence
- visual search
- image features
- relevance model