Poirot at CMCL 2022 Shared Task: Zero Shot Crosslingual Eye-Tracking Data Prediction using Multilingual Transformer Models

Harshvardhan Srivastava

Keywords: transformers, zero-shot, multilingual, cross-lingual

TL;DR: System Description Paper for prediction of Eye Tracking Features using some hand engineered features and multilingual transformer

Abstract:

Eye tracking data during reading is a useful source of information to understand the cognitive processes that take place during language comprehension processes. Different languages account for different cognitive triggers, however there seems to be some uniform indicators
across languages. In this paper, we describe our submission to the CMCL 2022 shared task on predicting human reading patterns for multi-lingual dataset. Our model uses text representations from transformers and some hand engineered features with a regression layer on top to predict statistical measures of mean and standard deviation for 2 main eye-tracking features. We train an end-to-end model to extract meaningful information from different languages and test our model on two separate datasets. We compare different transformer models and
show ablation studies affecting model performance. Our final submission ranked 4th place for SubTask-1 and 1st place for SubTask-2 for
the shared task.