TY - GEN
T1 - AttSum
T2 - 26th International Conference on Computational Linguistics, COLING 2016
AU - Cao, Ziqiang
AU - Li, Wenjie
AU - Li, Sujian
AU - Wei, Furu
AU - Li, Yanran
PY - 2016/1/1
Y1 - 2016/1/1
N2 - Query relevance ranking and sentence saliency ranking are the two main tasks in extractive query-focused summarization. Previous supervised summarization systems often perform the two tasks in isolation. However, since reference summaries are the trade-off between relevance and saliency, using them as supervision, neither of the two rankers could be trained well. This paper proposes a novel summarization system called AttSum, which tackles the two tasks jointly. It automatically learns distributed representations for sentences as well as the document cluster. Meanwhile, it applies the attention mechanism to simulate the attentive reading of human behavior when a query is given. Extensive experiments are conducted on DUC query-focused summarization benchmark datasets. Without using any hand-crafted features, AttSum achieves competitive performance. We also observe that the sentences recognized to focus on the query indeed meet the query need.
AB - Query relevance ranking and sentence saliency ranking are the two main tasks in extractive query-focused summarization. Previous supervised summarization systems often perform the two tasks in isolation. However, since reference summaries are the trade-off between relevance and saliency, using them as supervision, neither of the two rankers could be trained well. This paper proposes a novel summarization system called AttSum, which tackles the two tasks jointly. It automatically learns distributed representations for sentences as well as the document cluster. Meanwhile, it applies the attention mechanism to simulate the attentive reading of human behavior when a query is given. Extensive experiments are conducted on DUC query-focused summarization benchmark datasets. Without using any hand-crafted features, AttSum achieves competitive performance. We also observe that the sentences recognized to focus on the query indeed meet the query need.
UR - http://www.scopus.com/inward/record.url?scp=85029373061&partnerID=8YFLogxK
M3 - Conference article published in proceeding or book
AN - SCOPUS:85029373061
SN - 9784879747020
T3 - COLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016: Technical Papers
SP - 547
EP - 556
BT - COLING 2016 - 26th International Conference on Computational Linguistics, Proceedings of COLING 2016
PB - Association for Computational Linguistics, ACL Anthology
Y2 - 11 December 2016 through 16 December 2016
ER -