Abstract
Pronoun resolution plays an important role in language comprehension. However, little is known about its recruited cognitive mechanisms. Our investigation aims to explore the cognitive mechanisms underlying various types of pronoun resolution in Chinese using an electroencephalograph (EEG). We used three convolutional neural networks (CNNs)—LeNeT-5, GoogleNet, and EffifcientNet—to discover high-level feature abstractions of the EEG spatial topologies. The output of the three models was then fused using different scales by principal component analysis (PCA) to achieve cognitive workload classification. Overall, the workload classification rate by fusing three deep networks can be achieved at 55–63% in a participant-specific manner. We provide evidence that both the behavioral indicator of reaction time and the neural indicator of cognitive workload collected during pronoun resolution vary depending on the type of the pronoun. We observed an increase in reaction time accompanied by a decrease of the theta power while participants were processing ambiguous pronoun resolution compared to unambiguous controls. We propose that ambiguous pronoun resolution involves a more time-consuming yet more flexible cognitive mechanism, consistent with the predictions of the decision-making framework from an influential pragmatic tradition. Our results extend previous research that the cognitive states of resolving ambiguous and unambiguous pronouns are differentiated, indicating that cognitive workload evaluated using the method of machine learning for analysis of EEG signals acts as a complementary indicator for studying pronoun resolution and serves as an important inspiration for human–machine interaction.
Highlights
The current study aims to explore the cognitive mechanisms of pronoun resolution for two types of pronouns: unambiguous and ambiguous pronouns
According to the analysis of participants’ performances on the pronoun resolution trials, their reaction times, and the EEG distributions, we discover that the change of the trials, their reaction times, and the EEG distributions, we discover that the change of the manipulated task condition can induce the variation of the external behavior indicator of manipulated task condition can induce the variation of the external behavior indicator of the main task
A greater cognitive workload was required when a participant realized that the cognitive task had a standard answer in the cases of unambiguous pronoun resolution
Summary
A referential pronoun is often used to denote an previously mentioned individual [1]. A significant role of pronouns is to connect new information to what has already been presented in the context [2]. Pronoun resolution is a fundamental process in language comprehension [3]. It is argued that the readers determine pronoun referents mainly based on the gender of the pronoun [4], this task is complicated by the fact that pronouns may present referential ambiguity, where the gender information is insufficient for referent identification. The resolution of ambiguous pronouns, which pose a challenge in language comprehension, has aroused wide interest in the transdisciplinary research field of linguistics, psychology, neuroscience, and machine learning. The Google AI team has recently presented and released a genderbalanced corpus of 8908 ambiguous pronoun–noun pairs based on real-world text [5]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
