MTGER: Multi-view Temporal Graph Enhanced Temporal Reasoning over Time-Involved Document
This addresses the problem of improving temporal reasoning in NLP for applications like question answering, though it appears incremental by building on prior implicit modeling approaches.
The paper tackles the challenge of temporal reasoning over documents with intertwined facts and time by proposing MTGER, a multi-view temporal graph framework that explicitly models temporal relationships, achieving effectiveness on TimeQA and SituatedQA datasets and providing more consistent answers under perturbations.
The facts and time in the document are intricately intertwined, making temporal reasoning over documents challenging. Previous work models time implicitly, making it difficult to handle such complex relationships. To address this issue, we propose MTGER, a novel Multi-view Temporal Graph Enhanced Temporal Reasoning framework for temporal reasoning over time-involved documents. Concretely, MTGER explicitly models the temporal relationships among facts by multi-view temporal graphs. On the one hand, the heterogeneous temporal graphs explicitly model the temporal and discourse relationships among facts; on the other hand, the multi-view mechanism captures both time-focused and fact-focused information, allowing the two views to complement each other through adaptive fusion. To further improve the implicit reasoning capability of the model, we design a self-supervised time-comparing objective. Extensive experimental results demonstrate the effectiveness of our method on the TimeQA and SituatedQA datasets. Furthermore, MTGER gives more consistent answers under question perturbations.