Only One Relation Possible? Modeling the Ambiguity in Event Temporal Relation Extraction

Event Temporal Relation Extraction (ETRE) aims to identify the temporal relationship between two events, which plays an important role in natural language understanding. Most previous works follow a single-label classification style, classifying an event pair into either a specific temporal relation (e.g., textitBefore, textitAfter), or a special label textitVague when there may be multiple possible temporal relations between the pair. In our work, instead of directly making predictions on textitVague, we propose a multi-label classification solution for ETRE (METRE) to infer the possibility of each temporal relation independently, where we treat textitVague as the cases when there is more than one possible relation between two events. We design a speculation mechanism to explore the possible relations hidden behind textitVague, which enables the latent information to be used efficiently. Experiments on TB-Dense, MATRES and UDS-T show that our method can effectively utilize the textitVague instances to improve the recognition for specific temporal relations and outperforms most state-of-the-art methods.