Sophia Ananiadou

A Walk-based Model on Entity Graphs for Relation Extraction

2019 · arXiv (Cornell University)

We present a novel graph-based neural network model for relation extraction. Our model treats multiple pairs in a sentence simultaneously and considers interactions among them. All the entities in a sentence are placed as nodes …

Cluster-Level Contrastive Learning for Emotion Recognition in Conversations

2023 · IEEE Transactions on Affective Computing

A key challenge for Emotion Recognition in Conversations (ERC) is to distinguish semantically similar emotions. Some works utilise Supervised Contrastive Learning (SCL) which uses categorical emotion labels as supervision signals and contrasts in high-dimensional semantic …

Neuron-Level Knowledge Attribution in Large Language Models

2023 · Research Explorer (The University of Manchester)

Identifying important neurons for final predictions is essential for understanding the mechanisms of large language models. Due to computational constraints, current attribution techniques struggle to operate at neuron level. In this paper, we propose a …

Connecting the Dots: Document-level Neural Relation Extraction with Edge-oriented Graphs

2019

Fenia Christopoulou, Makoto Miwa, Sophia Ananiadou. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.