This project note describes challenges and procedures undertaken in annotating an audiovisual dataset capturing a multimodal situated collaborative construction task. In the task, all participants begin with different partial information, and must collaborate using speech, gesture, and action to arrive a solution that satisfies all individual pieces of private information. This rich data poses a number of annotation challenges, from small objects in a close space, to the implicit and multimodal fashion in which participants express agreement, disagreement, and beliefs. We discuss the data collection procedure, annotation schemas and tools, and future use cases.

We present a novel graph autoencoder (GAE) architecture for classifying gestures using Gesture Abstract Meaning Representation (GAMR), a structured semantic annotation framework for gestures in collaborative tasks. We leverage the inherent graphical structure of GAMR by employing Graph Neural Networks (GNNs), specifically an Edge-aware Graph Attention Network (EdgeGAT), to learn embeddings of gesture semantic representations. Using the EGGNOG dataset, which captures diverse physical gesture forms expressing similar semantics, we evaluate our GAE on a multi-label classification task for gestural actions. Results indicate that our approach significantly outperforms naive baselines and is competitive with specialized Transformer-based models like AMRBART, despite using considerably fewer parameters and no pretraining. This work highlights the effectiveness of structured graphical representations in modeling multimodal semantics, offering a scalable and efficient approach to gesture interpretation in situated human-agent collaborative scenarios.

Event coreference resolution (ECR) is the task of determining whether distinct mentions of events within a multi-document corpus are actually linked to the same underlying occurrence. Images of the events can help facilitate resolution when language is ambiguous. Here, we propose a multimodal cross-document event coreference resolution method that integrates visual and textual cues with a simple linear map between vision and language models. As existing ECR benchmark datasets rarely provide images for all event mentions, we augment the popular ECB+ dataset with event-centric images scraped from the internet and generated using image diffusion models. We establish three methods that incorporate images and text for coreference: 1) a standard fused model with finetuning, 2) a novel linear mapping method without finetuning and 3) an ensembling approach based on splitting mention pairs by semantic and discourse-level difficulty. We evaluate on 2 datasets: the augmented ECB+, and AIDA Phase 1. Our ensemble systems using cross-modal linear mapping establish an upper limit (91.9 CoNLL F1) on ECB+ ECR performance given the preprocessing assumptions used, and establish a novel baseline on AIDA Phase 1. Our results demonstrate the utility of multimodal information in ECR for certain challenging coreference problems, and highlight a need for more multimodal resources in the coreference resolution space.