Hanyin Wang, Chufan Gao, Qiping Xu, Bolun Liu, Guleid Hussein, Hariprasad Reddy Korsapati, Mohamad El Labban, Kingsley Iheasirim, Mohamed Hassan, Gokhan Anil, Brian Bartlett, Jimeng Sun. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Document-level relation extraction aims to categorize the association between any two entities within a document.We find that previous methods for document-level relation extraction are ineffective in exploiting the full potential of large amounts of training data with varied noise levels.For example, in the ReDo-cRED benchmark dataset, state-of-the-art methods trained on the large-scale, lower-quality, distantly supervised training data generally do not perform better than those trained solely on the smaller, high-quality, human-annotated training data.To unlock the full potential of large-scale noisy training data for documentlevel relation extraction, we propose TTM-RE, a novel approach that integrates a trainable memory module, known as the Token Turing Machine, with a noisy-robust loss function that accounts for the positive-unlabeled setting.Extensive experiments on ReDocRED, a benchmark dataset for document-level relation extraction, reveal that TTM-RE achieves state-ofthe-art performance (with an absolute F1 score improvement of over 3%).Ablation studies further illustrate the superiority of TTM-RE in other domains (the ChemDisGene dataset in the biomedical domain) and under highly unlabeled settings.

Problem solving is one of the most important 21st century skills. However, effectively coaching young students in problem solving is challenging because teachers must continuously monitor their cognitive and affective states and make real-time pedagogical interventions to maximize students' learning outcomes. It is an even more challenging task in social environments with limited human coaching resources. To lessen the cognitive load on a teacher and enable affect-sensitive intelligent tutoring, many researchers have investigated automated cognitive and affective detection methods. However, most of the studies use culturally-sensitive indices of affect that are prone to social editing such as facial expressions, and only few studies have explored involuntary dynamic behavioral signals such as gross body movements. In addition, most current methods rely on expensive labelled data from trained annotators for supervised learning. In this paper, we explore a semi-supervised learning framework that can learn low-dimensional representations of involuntary dynamic behavioral signals (mainly gross-body movements) from a modest number of short time series segments. Experiments on a real-world dataset reveal a significant utility of these representations in discriminating cognitive disequilibrium and flow and demonstrate their potential in transferring learned models to previously unseen subjects.

Engaged learners are effective learners. Even though it is widely recognized that engagement plays a vital role in learning effectiveness, engagement remains to be an elusive psychological construct that is yet to find a consensus definition and reliable measurement. In this study, we attempted to discover the plausible operational definitions of engagement within an online learning context. We achieved this goal by first deriving a set of interpretable features on dynamics of eyes, head and mouth movement from facial landmarks extractions of video recording when students interacting with an online tutoring system. We then assessed their predicative value for engagement which was approximated by synchronized measurements from commercial EEG brainwave headset worn by students. Our preliminary results show that those features reduce root mean-squared error by 29% compared with default predictor and we found that the random forest model performs better than a linear regressor.