CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals

TL;DR

CogAlign introduces a novel method to align textual neural representations with cognitive signals, improving NLP task performance and enabling transfer of cognitive information across datasets.

Contribution

The paper proposes CogAlign, a shared encoder with modality discrimination and text-aware attention to better integrate cognitive signals into NLP models.

Findings

Significant performance improvements on NER, sentiment analysis, and relation extraction.

Effective transfer of cognitive information to datasets without cognitive signals.

Outperforms state-of-the-art models using cognitive features.

Abstract

Most previous studies integrate cognitive language processing signals (e.g., eye-tracking or EEG data) into neural models of natural language processing (NLP) just by directly concatenating word embeddings with cognitive features, ignoring the gap between the two modalities (i.e., textual vs. cognitive) and noise in cognitive features. In this paper, we propose a CogAlign approach to these issues, which learns to align textual neural representations to cognitive features. In CogAlign, we use a shared encoder equipped with a modality discriminator to alternatively encode textual and cognitive inputs to capture their differences and commonalities. Additionally, a text-aware attention mechanism is proposed to detect task-related information and to avoid using noise in cognitive features. Experimental results on three NLP tasks, namely named entity recognition, sentiment analysis and relation extraction, show that CogAlign achieves significant improvements with multiple cognitive features over state-of-the-art models on public datasets. Moreover, our model is able to transfer cognitive information to other datasets that do not have any cognitive processing signals.