Log In Sign Up

SupMMD: A Sentence Importance Model for Extractive Summarization using Maximum Mean Discrepancy

by   Umanga Bista, et al.

Most work on multi-document summarization has focused on generic summarization of information present in each individual document set. However, the under-explored setting of update summarization, where the goal is to identify the new information present in each set, is of equal practical interest (e.g., presenting readers with updates on an evolving news topic). In this work, we present SupMMD, a novel technique for generic and update summarization based on the maximum mean discrepancy from kernel two-sample testing. SupMMD combines both supervised learning for salience and unsupervised learning for coverage and diversity. Further, we adapt multiple kernel learning to make use of similarity across multiple information sources (e.g., text features and knowledge based concepts). We show the efficacy of SupMMD in both generic and update summarization tasks by meeting or exceeding the current state-of-the-art on the DUC-2004 and TAC-2009 datasets.


page 1

page 2

page 3

page 4


Combining Word Embeddings and N-grams for Unsupervised Document Summarization

Graph-based extractive document summarization relies on the quality of t...

Attend to the beginning: A study on using bidirectional attention for extractive summarization

Forum discussion data differ in both structure and properties from gener...

An Unsupervised Masking Objective for Abstractive Multi-Document News Summarization

We show that a simple unsupervised masking objective can approach near s...


We propose and discuss the summarization of superpixel-type image tiles/...

Belief Propagation for Maximum Coverage on Weighted Bipartite Graph and Application to Text Summarization

We study text summarization from the viewpoint of maximum coverage probl...

A Formal Definition of Importance for Summarization

Research on summarization has mainly been driven by empirical approaches...

Extractive Summarization of Call Transcripts

Text summarization is the process of extracting the most important infor...