A compositional context sensitive multi-document summarizer: exploring the factors that influence summarization

By Ani Nenkova, Lucy Vanderwende, K. McKeown. 2006

261 citations recorded by the source corpus.

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

Determinantal Point Processes for Machine Learning (2012, background): “This selection problem is a balancing act: on the one hand, each selected sentence should be relevant, sharing significant information with the cluster as a whole; on the other, the selected sentences should be diverse as a group so that the summary is not repetitive and is as informative as possibl”
Ranking Sentences for Extractive Summarization with Reinforcement Learning (2018, methodology): “Traditional summarization methods manually define features to rank sentences for their salience in order to identify the most important sentences in a document or set of documents (Kupiec et al., 1995; Mani, 2001; Radev et al., 2004; Filatova and Hatzivassiloglou, 2004; Nenkova et al., 2006; Spärck ”
HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization (2019, background): “Early work with these models above mostly leverage human engineered features such as sentence position and length (Radev et al., 2004), word frequency (Nenkova et al., 2006) and event features (Filatova and Hatzivassiloglou, 2004b).”
A Survey of Text Summarization Techniques (2012, background): “The word probability approaches in the spirit of SumBasic [68] can directly ap-”
A Supervised Approach to Extractive Summarisation of Scientific Papers (2017, background): “Exploration of more cues such as sentence position (Yang et al., 2017), sentence length (Radev et al., 2004), words in the title, presence of proper nouns, word frequency (Nenkova et al., 2006) and event cues (Filatova and Hatzivassiloglou, 2004) followed.”
Improving the Estimation of Word Importance for News Multi-Document Summarization (2014, methodology): “The approach is similar to the standard word probability baseline (Nenkova et al., 2006) but we explore a range of possibilities for assigning weights to individual words.”
Improving the Estimation of Word Importance for News Multi-Document Summarization - Extended Technical Report (2016, methodology): “The approach is similar to the standard word probability baseline (Nenkova et al., 2006) but we explore a range of possibilities for assigning weights to individual words.”
From Extractive to Abstractive Summarization: A Journey (2019, methodology): “One such technique proposed by [58] estimates of word frequencies using a background corpus, and then ranks sentences based on the number of highly frequent words that it contains.”
Extractive Summarization Using Supervised and Semi-Supervised Learning (2008, background): “Lin and Hovy (2000) identified signature terms that were strongly associated with documents based on statistics measures.”
Neural Extractive Summarization with Side Information (2017, background): “(Nenkova et al., 2006) and low-level event-based features describing relationships between important actors in a document (Filatova, 2004).”
Near-Optimal MAP Inference for Determinantal Point Processes (2012, background): “Informative subset selection problems arise in many applications where a small number of items must be chosen to represent or cover a much larger set; for instance, text summarization [1, 2], document and image search [3, 4, 5], sensor placement [6], viral marketing [7], and many others.”
Graph-based Neural Multi-Document Summarization (2017, background): “FreqSum (Nenkova et al., 2006) 35.”
Enhancing Single-Document Summarization by Combining RankNet and Third-Party Sources (2007, methodology): “Sentence scoring methods utilize both purely statistical and purely semantic features, for example as in (Vanderwende et al., 2006; Nenkova et al., 2006; Yih et al., 2007).”
Im2Text: Describing Images Using 1 Million Captioned Photographs (2011, unknown): “Bad”
Neural Summarization by Extracting Sentences and Words (2016, background): “, 2004), the words in the title, the presence of proper nouns, content features such as word frequency (Nenkova et al., 2006), and event features such as action nouns (Filatova and Hatzivassiloglou, 2004).”
System Combination for Multi-document Summarization (2015, methodology): “ProbSum : This system (Nenkova et al., 2006) scores a sentence by taking the average of word probabilities over the words in the sentence, with stopwords assigned zero weights.”
Beyond SumBasic: Task-focused summarization with sentence simplification and lexical expansion (2007, methodology): “The system resembles SUMavr as recently described in Nenkova et al. (2006), except that the update function in SumBasic uses squaring rather than multiplication by a very small number.”
Benchmarking Large Language Models for News Summarization (2023, unknown): “In this work, we benchmark LLMs on news summarization to understand their potential for automatic summarization and focus on two popular news summarization benchmarks, CNN/DM (Hermann et al., 2015) and XSUM (Narayan et al., 2018).”