Fast and Robust Compressive Summarization with Dual Decomposition and Multi-Task Learning
نویسندگان
چکیده
We present a dual decomposition framework for multi-document summarization, using a model that jointly extracts and compresses sentences. Compared with previous work based on integer linear programming, our approach does not require external solvers, is significantly faster, and is modular in the three qualities a summary should have: conciseness, informativeness, and grammaticality. In addition, we propose a multi-task learning framework to take advantage of existing data for extractive summarization and sentence compression. Experiments in the TAC2008 dataset yield the highest published ROUGE scores to date, with runtimes that rival those of extractive summarizers.
منابع مشابه
Priberam Compressive Summarization Corpus: A New Multi-Document Summarization Corpus for European Portuguese
In this paper, we introduce the Priberam Compressive Summarization Corpus, a new multi-document summarization corpus for European Portuguese. The corpus follows the format of the summarization corpora for English in recent DUC and TAC conferences. It contains 80 manually chosen topics referring to events occurred between 2010 and 2013. Each topic contains 10 news stories from major Portuguese n...
متن کاملCascaded Attention based Unsupervised Information Distillation for Compressive Summarization
When people recall and digest what they have read for writing summaries, the important content is more likely to attract their attention. Inspired by this observation, we propose a cascaded attention based unsupervised model to estimate the salience information from the text for compressive multi-document summarization. The attention weights are learned automatically by an unsupervised data rec...
متن کاملPrimal and dual robust counterparts of uncertain linear programs: an application to portfolio selection
This paper proposes a family of robust counterpart for uncertain linear programs (LP) which is obtained for a general definition of the uncertainty region. The relationship between uncertainty sets using norm bod-ies and their corresponding robust counterparts defined by dual norms is presented. Those properties lead us to characterize primal and dual robust counterparts. The researchers show t...
متن کاملRobust uncapacitated multiple allocation hub location problem under demand uncertainty: minimization of cost deviations
The hub location–allocation problem under uncertainty is a real-world task arising in the areas such as public and freight transportation and telecommunication systems. In many applications, the demand is considered as inexact because of the forecasting inaccuracies or human’s unpredictability. This study addresses the robust uncapacitated multiple allocation hub location problem with a set of ...
متن کاملThe Role of working memory capacity on the learning the relative timing a motor task: Emphasis on implicit and explicit approaches
Abstract The aim of this study was to investigate the role of working memory capacity and errorless and errorful practice on the learning the relative timing was a motor task. 50 Participants based on were selected aged 22±4 years as accessible samples randomly assigned to one of four groups (errorless low working memory capacity, errorful low working memory capacity, errorless high working me...
متن کامل