Hedge Trimmer: A Parse-and-Trim Approach to Headline Generation

By Bonnie J. Dorr, David M. Zajic, Richard M. Schwartz. 2003

289 citations recorded by the source corpus.

This paper presents Hedge Trimmer, a HEaDline GEneration system that creates a headline for a newspaper story using linguistically-motivated heuristics to guide the choice of a potential headline. We present feasibility tests used to establish the validity of an approach that constructs a headline by selecting words in order from a story. In addition, we describe experimental results that demonstrate the effectiveness of our linguistically-motivated approach over a HMM-based model, using both human evaluation and automatic metrics for comparing the two approaches.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

A Deep Reinforced Model for Abstractive Summarization (2017, methodology): “Most abstractive summarization models have been evaluated on the DUC-2004 dataset, and outperform extractive models on that task (Dorr et al., 2003).”
MLSUM: The Multilingual Summarization Corpus (2020, methodology): “…of training data available, DUC datasets are often used in a domain adaptation setup for models ﬁrst trained on larger datasets such as Gigaword, CNN/DM (Nallapati et al., 2016; See et al., 2017) or with unsupervised methods (Dorr et al., 2003; Mihalcea and Tarau, 2004; Barrios et al., 2016a).”
Learning to summarize from human feedback (2020, background): “To make short-term progress towards this goal, we focus on abstractive English text summarization, as it has a long history in the NLP community [16, 8, 54, 59, 50], and is a subjective task where we believe it is difficult to quantify summary quality without human judgments.”
A Neural Attention Model for Abstractive Sentence Summarization (2015, methodology): “TOPIARY merges a compression system using linguisticallymotivated transformations of the input (Dorr et al., 2003) with an unsupervised topic detection (UTD) algorithm that appends key phrases from the full article onto the compressed output.”
Bottom-Up Abstractive Summarization (2018, methodology): “For example, Dorr et al. (2003) introduced a system that ﬁrst extracts noun and verb phrases from the ﬁrst sentence of a news article and uses an iterative shortening algorithm to compress it.”
Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies (2018, methodology): “The data have also been used to evaluate unsupervised methods (Dorr et al., 2003; Mihal-cea and Tarau, 2004; Barrios et al., 2016).”
Evaluating the Factual Consistency of Abstractive Text Summarization (2019, background): “Common approaches to summarization are extractive (Dorr et al., 2003; Nallapati et al., 2017) where models directly copy salient parts of the source document into the summary, abstractive (Rush et al.”
Neural Text Summarization: A Critical Evaluation (2019, background): “Two strategies of generating summaries are extractive (Dorr et al., 2003; Nallapati et al., 2017), where salient fragments of the source document are identiﬁed and directly copied into the summary, and abstractive (Rush et al., 2015; See et al., 2017), where the salient parts are detected and…”
Controlling Output Length in Neural Encoder-Decoders (2016, methodology): “In particular, in this paper we focus on sentence summarization, which as its name suggests, consists of generating shorter versions of sentences for applications such as document summarization (Nenkova and McKeown, 2011) or headline generation (Dorr et al., 2003).”
Overcoming the Lack of Parallel Data in Sentence Compression (2013, methodology): “To decide which words, dependencies or phrases can be dropped, (i) rule-based approaches (Grefenstette, 1998; Jing & McKeown, 2000; Dorr et al., 2003; Zajic et al., 2007), (ii) supervised models trained on parallel data (Knight & Marcu, 2000; Turner & Charniak, 2005; McDonald, 2006; Gillick &…”
Improving Abstraction in Text Summarization (2018, methodology): “The two most common approaches to summarization are extractive (Dorr et al., 2003; Nallapati et al., 2017), where the model extracts salient parts of the source document, and abstractive (Paulus et al.”
Neural Headline Generation with Minimum Risk Training (2016, methodology): “When the generated summary is required to be a single compact sentence, we name the summarization task as headline generation [4].”
PathVQA: 30000+ Questions for Medical Visual Question Answering (2020, methodology): “Given the subjects, verbs, clauses, etc. labeled by POS tagging and syntactic parsing, we rearrange them using the rules proposed in [16, 17] to achieve simpliﬁcation.”
Automatic Caption Generation for News Images (2013, methodology): “Duygulu et al. (2002) segment images into regions and cluster the latter using Kmeans into 500 classes which they call blobs.”
Selective Encoding for Abstractive Sentence Summarization (2017, methodology): “There are some previous methods to solve this task, such as the linguistic rule-based method (Dorr et al., 2003).”
How Many Words Is a Picture Worth? Automatic Caption Generation for News Images (2010, background): “The caption generation task bears some resemblance to headline generation (Dorr et al., 2003; Banko et al., 2000; Jin and Hauptmann, 2002) where the aim is to create a very short summary for a document.”
Automatic Generation of Story Highlights (2010, background): “Our approach bears some resemblance to headline generation (Dorr et al., 2003; Banko et al., 2000), although we output several sentences rather than a single one.”
Global Encoding for Abstractive Summarization (2018, methodology): “Researchers developed many statistical methods and linguistic-rule-based methods to study automatic summarization (Banko et al., 2000; Dorr et al., 2003; Zajic et al., 2004; Cohn and Lapata, 2008).”
Title Generation with Quasi-Synchronous Grammar (2010, background): “Additional operations include truncating sentences, aggregating them, and paraphrasing at word or syntax level.”