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

by   Junru Lu, et al.
King's College London
University of Warwick

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 fine-tuned 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 Match (EM) score under the multi-answer 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.


page 1

page 2

page 3

page 4


Event-QA: A Dataset for Event-Centric Question Answering over Knowledge Graphs

Semantic Question Answering (QA) is the key technology to facilitate int...

Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering

We propose a simple yet effective strategy to incorporate event knowledg...

Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering

Question Answering (QA) models over Knowledge Bases (KBs) are capable of...

Event Detection as Question Answering with Entity Information

In this paper, we propose a recent and under-researched paradigm for the...

TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events

Traffic event cognition and reasoning in videos is an important task tha...

Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering

Existing knowledge-enhanced methods have achieved remarkable results in ...

Please sign up or login with your details

Forgot password? Click here to reset