FAMuS: Frames Across Multiple Sources

Code

• github.com/factslab/famus
  OfficialIn paperpytorch★ 5
• github.com/wgantt/eae-transfer
  pytorch★ 1

Abstract

Understanding event descriptions is a central aspect of language processing, but current approaches focus overwhelmingly on single sentences or documents. Aggregating information about an event across documents can offer a much richer understanding. To this end, we present FAMuS, a new corpus of Wikipedia passages that report on some event, paired with underlying, genre-diverse (non-Wikipedia) source articles for the same event. Events and (cross-sentence) arguments in both report and source are annotated against FrameNet, providing broad coverage of different event types. We present results on two key event understanding tasks enabled by FAMuS: source validation -- determining whether a document is a valid source for a target report event -- and cross-document argument extraction -- full-document argument extraction for a target event from both its report and the correct source article. We release both FAMuS and our models to support further research.

Tasks

Reproductions