Automatic summarization of English broadcast news speech

By Chiori Hori, Sadaoki Furui, Robert G. Malkin, Hua Yu, Alex Waibel. 2002

776 citations recorded by the source corpus.

This paper proposes an automatic speech summarization technique for English. In our proposed method, a set of words maximizing a summarization score indicating appropriateness of summarization is extracted from automatically transcribed speech and concatenated to create a summary. The extraction process is performed using a Dynamic Programming (DP) technique according to a target compression ratio. In this paper, English broadcast news speech transcribed using a speech recognizer is automatically summarized. In order to apply our method, originally proposed for Japanese, to English, the model of estimating word concatenation probabilities based on a dependency structure in the original speech given by a Stochastic Dependency Context Free Grammar (SDCFG) is modified. A summarization method for multiple utterances using two-level DP technique is also proposed. The automatically summarized sentences are evaluated by a summarization accuracy based on the comparison with the manual summarization of correctly transcribed speech by human subjects. Experimental results show that our proposed method effectively extracts relatively important information and remove redundant and irrelevant information from English news speech.

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

Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization (2018, background): “Of the many summarization paradigms that have been identiﬁed over the years (see Mani, 2001 and Nenkova and McKeown, 2011 for a comprehensive overview), single-document summarization has consistently attracted attention (Cheng and Lapata, 2016; Durrett et al., 2016; Nallapati et al., 2016, 2017;…”
On Faithfulness and Factuality in Abstractive Summarization (2020, background): “By deﬁnition, abstractive summaries are written to preserve the salient information in the input document, but they are expressed in the words of the summary author as opposed to the input document author (Nenkova and McKeown, 2011).”
Controllable Abstractive Summarization (2017, background): “Efforts in both extractive and abstractive meth-ods have followed advances in the ﬁeld of natural language processing, pattern recognition, and machine learning (Nenkova et al., 2011).”
Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints (2016, background): “While multi-document summarization is wellstudied in the NLP literature (Carbonell and Goldstein, 1998; Gillick and Favre, 2009; Lin and Bilmes, 2011; Nenkova and McKeown, 2011), single-document summarization (McKeown et al.”
Ranking Sentences for Extractive Summarization with Reinforcement Learning (2018, background): “Single document summarization — the task of producing a shorter version of a document while preserving its information content — is perhaps the most basic of summarization tasks that have been identiﬁed over the years (see Nenkova and McKeown, 2011 for a comprehensive overview).”
Hedge Trimmer: A Parse-and-Trim Approach to Headline Generation (2003, background): “…1995; Mann et al., 1992; Teufel and Moens, 1997; Zechner, 1995), processing of structured templates (Paice and Jones, 1993), sentence compression (Hori et al., 2002; Knight and Marcu, 2001; Grefenstette, 1998, Luhn, 1958), and generation of abstracts from multiple sources (Radev and McKeown,…”
Overcoming the Lack of Parallel Data in Sentence Compression (2013, methodology): “A robust compression system would be useful for mobile devices as well as a module in an extractive summarization system (Mani, 2001).”
LCSTS: A Large Scale Chinese Short Text Summarization Dataset (2015, background): “Recently, recurrent neural network (RNN) have shown powerful abilities on speech recognition (Graves et al., 2013), machine translation (Sutskever et al., 2014) and automatic dialog response (Shang et al., 2015).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “…generation applications is beyond the scope of a single survey, and many of these are covered in other individual surveys, including Mani (2001) and Nenkova and McKeown (2011) for summarisation; Androutsopoulos and Malakasiotis (2010) for paraphrasing; and Piwek and Boyer (2012) for automatic…”
Neural Document Summarization by Jointly Learning to Score and Select Sentences (2018, background): “Traditional approaches to automatic text summarization focus on identifying important content, usually at sentence level (Nenkova and McKeown, 2011).”
Answers Unite! Unsupervised Metrics for Reinforced Summarization Models (2019, methodology): “Many unsupervised models, that aim at computing a score between a sentence and document(s) were developed – the score at-tempting to reﬂect whether the sentence should be selected for building a summary (Nenkova, 2011).”
Guiding Extractive Summarization with Question-Answering Rewards (2019, background): “Extractive summarization has seen growing popularity in the past decades (Nenkova and McKeown, 2011).”
Neural Latent Extractive Document Summarization (2018, background): “Of the many summarization paradigms that have been identiﬁed over the years (see Mani 2001 and Nenkova and McKeown 2011 for comprehensive overviews), two have consistently attracted attention: extractive approaches generate summaries by copying parts of the source document (usually whole…”
HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization (2019, background): “For a more comprehensive review of summarization, we refer the interested readers to Nenkova and McKeown (2011) and Mani (2001).”
Data-driven Summarization of Scientific Articles (2018, methodology): “Previous research on summarization of scientific articles has focused almost exclusively on extractive methods (Nenkova et al., 2011).”
Processing Social Media Messages in Mass Emergency (2014, methodology): “Text summarization refers to the generation of a text summary of a document or set of documents [Nenkova and McKeown 2011].”
Focus Attention: Promoting Faithfulness and Diversity in Summarization (2021, background): “Document summarization — producing the shorter version of a document while preserving salient information (Mani, 2001; Nenkova and McKeown, 2011) — is challenging even for humans.”
Main Core Retention on Graph-of-Words for Single-Document Keyword Extraction (2015, methodology): “We refer to the survey of Nenkova and McKeown in [20] for an in-depth review on automatic summarization and by extension on keyword extraction.”
Choosing words in computer-generated weather forecasts (2005, background): “Quite a bit of research has been done on generating textual summaries of textual information [21].”
Introduction to the Special Issue on Summarization (2002, background): “Frequent workshops and symposia reﬂect the ongoing interest of researchers around the world.”