Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation

Abstract

Human reading comprehension often requires reasoning of event semantic relations in narratives, represented by Event-centric Question-Answering (QA). To address event-centric QA, we propose a novel QA model with contrastive learning and invertible event transformation, call TranCLR. Our proposed model utilizes an invertible transformation matrix to project semantic vectors of events into a common event embedding space, trained with contrastive learning, and thus naturally inject event semantic knowledge into mainstream QA pipelines. The transformation matrix is finetuned with the annotated event relation types between events that occurred in questions and those in answers, using event-aware question vectors. Experimental results on the Event Semantic Relation Reasoning (ESTER) dataset show significant improvements in both generative and extractive settings compared to the existing strong baselines, achieving over 8.4% gain in the token-level F1 score and 3.0% gain in Exact Match (EM) score under the multianswer setting. Qualitative analysis reveals the high quality of the generated answers by TranCLR, demonstrating the feasibility of injecting event knowledge into QA model learning. Our code and models can be found at https://github.com/LuJunru/TranCLR.

MTGER: Multi-view Temporal Graph Enhanced Temporal Reasoning over Time-Involved Document

“…Reasoning focuses on the relative temporal relationship between events, including event temporal QA Lu et al, 2022;Han et al, 2021), temporal commonsense reasoning (Qin et al, 2021;Zhou et al, 2019, event timeline extraction (Faghihi et al, 2022), and temporal dependency parsing (Mathur et al, 2022). TranCLR (Lu et al, 2022) injects event semantic knowledge into QA pipelines through contrastive learning. ECONET (Han et al, 2021) equips PLMs with event temporal relations knowledge by continuing pre-training.…”