MTGER: Multi-view Temporal Graph Enhanced Temporal Reasoning over Time-Involved Document
Submission Type: Regular Long Paper
Submission Track: Question Answering
Submission Track 2: Question Answering
Keywords: Question Answering, Temporal Reasoning, Natural Language Processing
TL;DR: Inspired by the human reasoning process, we propose to model the temporal relationship between facts and time via temporal graphs, outperforming SOTA on two document-level temporal reasoning datasets, TimeQA and SituatedQA.
Abstract: 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 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.
Submission Number: 2900
Loading