Long story short - Global unsupervised models for keyphrase based meeting summarization

By K. Riedhammer, Benoit Favre, Dilek Z. Hakkani-Tür. 2010

98 citations recorded by the source corpus.

We analyze and compare two different methods for unsupervised extractive spontaneous speech summarization in the meeting domain. Based on utterance comparison, we introduce an optimal formulation for the widely used greedy maximum marginal relevance (MMR) algorithm. Following the idea that information is spread over the utterances in form of concepts, we describe a system which finds an optimal selection of utterances covering as many unique important concepts as possible. Both optimization problems are formulated as an integer linear program (ILP) and solved using public domain software. We analyze and discuss the performance of both approaches using various evaluation setups on two well studied meeting corpora. We conclude on the benefits and drawbacks of the presented models and give an outlook on future aspects to improve extractive meeting summarization.

Subfields: Artificial Intelligence

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

Citations in the corpus

Improving the Estimation of Word Importance for News Multi-Document Summarization (2014, methodology): “Earliest such work relied on TF*IDF weights (Filatova and Hatzivassiloglou, 2004), later approaches included heuristics to identify summary-worthy bigrams (Riedhammer et al., 2010).”
Recent automatic text summarization techniques: a survey (2016, background): “Summarization task can be either supervised or unsupervised (Mani and Maybury 1999; Fattah andRen 2009; Riedhammer et al. 2010).”
A Class of Submodular Functions for Document Summarization (2011, methodology): “…many well-established methods for summarization (Carbonell and Goldstein, 1998; Filatova and Hatzivassiloglou, 2004; Takamura and Okumura, 2009; Riedhammer et al., 2010; Shen and Li, 2010) correspond to submodular function optimization, a property not explicitly mentioned in these publications.”
Improving the Estimation of Word Importance for News Multi-Document Summarization - Extended Technical Report (2016, methodology): “Earliest such work relied on TF*IDF weights (Filatova and Hatzivassiloglou, 2004), later approaches included heuristics to identify summary-worthy bigrams (Riedhammer et al., 2010).”
Multiple documents summarization based on evolutionary optimization algorithm (2013, background): “These two aspects are usually addressed by computing separate scores and deciding for the best candidates regarding some relevance redundancy trade-off (Riedhammer et al., 2010).”
Abstractive text summarization using LSTM-CNN based deep learning (2018, background): “In a very recent work, Konstantin Lopyrev [19] describes an application of an encoder-decoder recurrent neural network with LSTM units and attention to generate headlines from the text of news articles.”
Self reinforcement for important passage retrieval (2013, background): “Closely related to our work are the unsupervised key phrase extraction approaches that have been explored to reinforce summarization [32, 29, 11, 22, 24].”
Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts (2018, background): “Therefore, speech summarization has been investigated in the past [14, 15, 16, 17, 18, 19].”
Natural language processing: state of the art, current trends and challenges (2017, background): “Summarization task can be either supervised or unsupervised (Mani and Maybury 1999 [74]; Fattah and Ren 2009 [43]; Riedhammer et al. 2010 [110]).”