System Combination for Multi-document Summarization

By Kai Hong, Mitchell P. Marcus, Ani Nenkova. 2015

32 citations recorded by the source corpus.

We present a novel framework of system combination for multi-document summarization. For each input set (input), we generate candidate summaries by combining whole sentences from the summaries generated by different systems. We show that the oracle among these candidates is much better than the summaries that we have combined. We then present a supervised model to select among the candidates. The model relies on a rich set of features that capture content importance from different perspectives. Our model performs better than the systems that we combined based on manual and automatic evaluations. We also achieve very competitive performance on six DUC/TAC datasets, comparable to the state-of-the-art on most datasets.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

A Deep Reinforced Model for Abstractive Summarization (2017, background): “…2014; Li et al., 2016) or closely-related models for predicting the importance of a phrase in an article (Yang and Nenkova, 2014; Nye and Nenkova, 2015; Hong et al., 2015), we are the ﬁrst group to run an end-to-end abstrac-tive summarization model on the article-abstract pairs of this dataset.”
Deep Communicating Agents for Abstractive Summarization (2018, methodology): “New York Times (NYT): Although this dataset has mainly been used to train extractive summarization systems (Hong and Nenkova, 2014; Hong et al., 2015; Li et al., 2016; Durrett et al., 2016), it has recently been used for the abstractive summarization task (Paulus et al., 2018).”
The Role of Discourse Units in Near-Extractive Summarization (2016, methodology): “(3)Note that this differs from the abstracts used in prior summarization research (Yang and Nenkova, 2014; Hong et al., 2015; Nye and Nenkova, 2015).”
From Extractive to Abstractive Summarization: A Journey (2019, background): “…these summaries at various levels, like fusing rank lists(Wang and Li, 2012), choosing the best combination of sentences from several summaries(Hong et al., 2015) or using learning-to-rank techniques to generate rank lists of sentences and then choosing the top-k sentences as a sum-mary, to…”
RefSum: Refactoring Neural Summarization (2021, methodology): “By contrast, Hong et al. (2015) focus on summaries generated from different systems and use a non-neural system combination method to make their complementary advantages.”
GSum: A General Framework for Guided Neural Abstractive Summarization (2020, methodology): “Thus, we can safely conclude that each type of guidance signal has its own merits and one promising direction is to utilize a system combination method such as Hong et al. (2015) to aggregate the results together.”
Recent automatic text summarization techniques: a survey (2016, methodology): “2015) Need: This approach is especially required to generate updates across time describing disastrous events which can serve the information needs of responders, crisis management organizations and victims Pros: The proposed approach that combines salience with clustering generates more relevant su”