Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Events

Abstract: Tracking entities throughout a procedure described in a text is challenging due to the dynamic nature of the world described in the process. Firstly, we propose to formulate this task as a question answering problem. This enables us to use pre-trained transformer-based LLMs on other QA benchmarks by adapting those to the procedural text understanding. Secondly, since the transformer-based LLMs cannot encode the flow of events by themselves, we propose a Time-Stamped LLM~(TSLM model) to encode event information in LMs architecture by introducing the timestamp encoding. Our model evaluated on the Propara dataset shows improvements on the published state-of-the-art results with a $3.1\%$ increase in F1 score. Moreover, our model yields better results on the location prediction task on the NPN-Cooking dataset. This result indicates that our approach is effective for procedural text understanding in general.