TY - JOUR
T1 - Document Summarization with Latent Queries
AU - Xu, Yumo
AU - Lapata, Mirella
N1 - Funding Information:
The authors would like to thank the action editor, Wenjie Li, and the anonymous reviewers for their valuable feedback. We acknowledge the financial support of the European Research Council (Lapata; award number 681760). This research was supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via contract FA8650-17-C-9118. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the ODNI, IARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.
Publisher Copyright:
© 2022 Association for Computational Linguistics. Distributed under a CC-BY 4.0 license.
PY - 2022/5/4
Y1 - 2022/5/4
N2 - The availability of large-scale datasets has driven the development of neural models that create generic summaries for single or multiple documents. For query-focused summarization (QFS), labeled training data in the form of queries, documents, and summaries is not readily available. We provide a unified modeling framework for any kind of summarization, under the assumption that all summaries are a response to a query, which is observed in the case of QFS and latent in the case of generic summarization. We model queries as discrete latent variables over document tokens, and learn representations compatible with observed and unobserved query verbalizations. Our framework formulates summarization as a generative process, and jointly optimizes a latent query model and a conditional language model. Despite learning from generic summarization data only, our approach outperforms strong comparison systems across benchmarks, query types, document settings, and target domains.1
AB - The availability of large-scale datasets has driven the development of neural models that create generic summaries for single or multiple documents. For query-focused summarization (QFS), labeled training data in the form of queries, documents, and summaries is not readily available. We provide a unified modeling framework for any kind of summarization, under the assumption that all summaries are a response to a query, which is observed in the case of QFS and latent in the case of generic summarization. We model queries as discrete latent variables over document tokens, and learn representations compatible with observed and unobserved query verbalizations. Our framework formulates summarization as a generative process, and jointly optimizes a latent query model and a conditional language model. Despite learning from generic summarization data only, our approach outperforms strong comparison systems across benchmarks, query types, document settings, and target domains.1
U2 - 10.1162/tacl_a_00480
DO - 10.1162/tacl_a_00480
M3 - Article
SN - 2307-387X
VL - 10
SP - 623
EP - 638
JO - Transactions of the Association for Computational Linguistics
JF - Transactions of the Association for Computational Linguistics
ER -