Cross-Lingual Transfer of Cognitive Processing Complexity
This work addresses cross-lingual cognitive modeling for researchers in NLP and cognitive science, but it is incremental as it applies an existing method to new data.
The study tackled the problem of predicting cognitive processing complexity across languages using multilingual models, showing that XLM-RoBERTa successfully predicted eye-tracking patterns for 13 diverse languages with fine-tuning only on English data, and quantified sensitivity to structural complexity including sentence length and cross-lingual differences.
When humans read a text, their eye movements are influenced by the structural complexity of the input sentences. This cognitive phenomenon holds across languages and recent studies indicate that multilingual language models utilize structural similarities between languages to facilitate cross-lingual transfer. We use sentence-level eye-tracking patterns as a cognitive indicator for structural complexity and show that the multilingual model XLM-RoBERTa can successfully predict varied patterns for 13 typologically diverse languages, despite being fine-tuned only on English data. We quantify the sensitivity of the model to structural complexity and distinguish a range of complexity characteristics. Our results indicate that the model develops a meaningful bias towards sentence length but also integrates cross-lingual differences. We conduct a control experiment with randomized word order and find that the model seems to additionally capture more complex structural information.