EIGEN: Event Influence GENeration using Pre-trained Language Models

Abstract

Reasoning about events and tracking their influences is fundamental to understanding processes. In this paper, we present EIGEN - a method to leverage pre-trained language models to generate event influences conditioned on a context, nature of their influence, and the distance in a reasoning chain. We also derive a new dataset for research and evaluation of methods for event influence generation. EIGEN outperforms strong baselines both in terms of automated evaluation metrics (by 10 ROUGE points) and human judgments on closeness to reference and relevance of generations. Furthermore, we show that the event influences generated by EIGEN improve the performance on a "what-if" Question Answering (WIQA) benchmark (over 3% F1), especially for questions that require background knowledge and multi-hop reasoning.

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• The Curious Case of Neural Text Degeneration
• ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
• Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation
• Data Augmentation using Pre-trained Transformer Models
• WIQA: A dataset for "What if..." reasoning over procedural text

Cited by in corpus (5)

• DAGN: Discourse-Aware Graph Network for Logical Reasoning
• Neural Language Modeling for Contextualized Temporal Graph Generation
• Conditional Generation of Temporally-ordered Event Sequences
• Relational Gating for "What If" Reasoning
• ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning