Lavinia Salicchi


2022

pdf
HkAmsters at CMCL 2022 Shared Task: Predicting Eye-Tracking Data from a Gradient Boosting Framework with Linguistic Features
Lavinia Salicchi | Rong Xiang | Yu-Yin Hsu
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics

Eye movement data are used in psycholinguistic studies to infer information regarding cognitive processes during reading. In this paper, we describe our proposed method for the Shared Task of Cognitive Modeling and Computational Linguistics (CMCL) 2022 - Subtask 1, which involves data from multiple datasets on 6 languages. We compared different regression models using features of the target word and its previous word, and target word surprisal as regression features. Our final system, using a gradient boosting regressor, achieved the lowest mean absolute error (MAE), resulting in the best system of the competition.

2021

pdf
Looking for a Role for Word Embeddings in Eye-Tracking Features Prediction: Does Semantic Similarity Help?
Lavinia Salicchi | Alessandro Lenci | Emmanuele Chersoni
Proceedings of the 14th International Conference on Computational Semantics (IWCS)

Eye-tracking psycholinguistic studies have suggested that context-word semantic coherence and predictability influence language processing during the reading activity. In this study, we investigate the correlation between the cosine similarities computed with word embedding models (both static and contextualized) and eye-tracking data from two naturalistic reading corpora. We also studied the correlations of surprisal scores computed with three state-of-the-art language models. Our results show strong correlation for the scores computed with BERT and GloVe, suggesting that similarity can play an important role in modeling reading times.

pdf
PIHKers at CMCL 2021 Shared Task: Cosine Similarity and Surprisal to Predict Human Reading Patterns.
Lavinia Salicchi | Alessandro Lenci
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics

Eye-tracking psycholinguistic studies have revealed that context-word semantic coherence and predictability influence language processing. In this paper we show our approach to predict eye-tracking features from the ZuCo dataset for the shared task of the Cognitive Modeling and Computational Linguistics (CMCL2021) workshop. Using both cosine similarity and surprisal within a regression model, we significantly improved the baseline Mean Absolute Error computed among five eye-tracking features.