Abstract
Determining whether an event in a news article is a foreground or background event would be useful in many natural language processing tasks, for example, temporal relation extraction, summarization, or storyline generation. We introduce the task of distinguishing between foreground and background events in news articles as well as identifying the general temporal position of background events relative to the foreground period (past, present, future, and their combinations). We achieve good performance (0.73 F1 for background vs. foreground and temporal position, and 0.79 F1 for background vs. foreground only) on a dataset of news articles by leveraging discourse information in a featurized model. We release our implementation and annotated data for other researchers
Highlights
Grimes et al (1975) defined foreground events as the events that form the skeleton of a story whereas background events add supporting information
We introduce the task of distinguishing between foreground and background events, as well as identifying the general temporal position of backgrounds events relative to the foreground period
Our contributions are as follows: (1) we introduce a new task, namely, distinguishing foreground and background events and marking the general temporal position of background events relative to the foreground period; (2) we provide an annotated corpus with high inter-annotated agreement; (3) we demonstrate a simple featurized model that achieves reasonable performance (0.73 F1 for background vs. foreground and temporal position, and 0.79 F1 for background vs. foreground only); and (4) we show the utility of this task for three different NLP tasks—subevent detection, event coreference resolution and temporal relation extraction—by showing improvements in performance between 1 and 5 points of F1
Summary
Grimes et al (1975) defined foreground events as the events that form the skeleton of a story whereas background events add supporting information. We introduce the task of distinguishing between foreground and background events, as well as identifying the general temporal position of backgrounds events relative to the foreground period (past, present, future, and their combinations). Identifying the general temporal position is a coarser analog to detailed, pairwise temporal relation extraction, and provides an intermediate step to ease the integration of discourse information into temporal understanding of the text. Background events add supporting or contextual information.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have