TY - GEN
T1 - In conclusion not repetition
T2 - 23rd Conference on Computational Natural Language Learning, CoNLL 2019
AU - Li, Lei
AU - Liu, Wei
AU - Litvak, Marina
AU - Vanetik, Natalia
AU - Huang, Zuying
N1 - Publisher Copyright:
© 2019 Association for Computational Linguistics.
PY - 2019/1/1
Y1 - 2019/1/1
N2 - Various Seq2Seq learning models designed for machine translation were applied for abstractive summarization task recently. Despite these models provide high ROUGE scores, they are limited to generate comprehensive summaries with a high level of abstraction due to its degenerated attention distribution. We introduce Diverse Convolutional Seq2Seq Model(DivCNN Seq2Seq) using Determinan-tal Point Processes methods(Micro DPPs and Macro DPPs) to produce attention distribution considering both quality and diversity. Without breaking the end to end architecture, DivCNN Seq2Seq achieves a higher level of comprehensiveness compared to vanilla models and strong baselines. All the reproducible codes and datasets are available online.
AB - Various Seq2Seq learning models designed for machine translation were applied for abstractive summarization task recently. Despite these models provide high ROUGE scores, they are limited to generate comprehensive summaries with a high level of abstraction due to its degenerated attention distribution. We introduce Diverse Convolutional Seq2Seq Model(DivCNN Seq2Seq) using Determinan-tal Point Processes methods(Micro DPPs and Macro DPPs) to produce attention distribution considering both quality and diversity. Without breaking the end to end architecture, DivCNN Seq2Seq achieves a higher level of comprehensiveness compared to vanilla models and strong baselines. All the reproducible codes and datasets are available online.
UR - http://www.scopus.com/inward/record.url?scp=85084337605&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85084337605
T3 - CoNLL 2019 - 23rd Conference on Computational Natural Language Learning, Proceedings of the Conference
SP - 822
EP - 832
BT - CoNLL 2019 - 23rd Conference on Computational Natural Language Learning, Proceedings of the Conference
PB - Association for Computational Linguistics
Y2 - 3 November 2019 through 4 November 2019
ER -