Human brain activity for machine attention
This work addresses the challenge of integrating neuroscientific data into machine learning for NLP, offering a novel approach that could enhance model interpretability and performance, though it is incremental in scope.
The authors tackled the problem of improving neural attention models in NLP by using EEG data from human brain activity, showing that EEG-informed attention outperforms strong baselines on relation classification tasks.
Cognitively inspired NLP leverages human-derived data to teach machines about language processing mechanisms. Recently, neural networks have been augmented with behavioral data to solve a range of NLP tasks spanning syntax and semantics. We are the first to exploit neuroscientific data, namely electroencephalography (EEG), to inform a neural attention model about language processing of the human brain. The challenge in working with EEG data is that features are exceptionally rich and need extensive pre-processing to isolate signals specific to text processing. We devise a method for finding such EEG features to supervise machine attention through combining theoretically motivated cropping with random forest tree splits. After this dimensionality reduction, the pre-processed EEG features are capable of distinguishing two reading tasks retrieved from a publicly available EEG corpus. We apply these features to regularise attention on relation classification and show that EEG is more informative than strong baselines. This improvement depends on both the cognitive load of the task and the EEG frequency domain. Hence, informing neural attention models with EEG signals is beneficial but requires further investigation to understand which dimensions are the most useful across NLP tasks.