HEADY: News headline abstraction through event pattern clustering
Venue
Proceedings of ACL-2013
Publication Year
2013
Authors
Enrique Alfonseca, Daniele Pighin, Guillermo Garrido
BibTeX
Abstract
This paper presents HEADY: a novel, ab- stractive approach for headline generation
from news collections. From a web-scale corpus of English news, we mine syntactic
patterns that a Noisy-OR model generalizes into event descriptions. At inference
time, we query the model with the patterns observed in an unseen news collection,
identify the event that better captures the gist of the collection and retrieve the
most appropriate pattern to generate a headline. HEADY improves over a
state-of-the- art open-domain title abstraction method, bridging half of the gap
that separates it from extractive methods using human-generated titles in manual
evaluations, and performs comparably to human-generated headlines as evaluated with
ROUGE.
