Temporal summaries of new topics

By James Allan, Rahul Gupta, V. Khandelwal. 2001

274 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Signal 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 Information Systems

In Signal Processing

Citations in the corpus

Determinantal Point Processes for Machine Learning (2012, background): “[2] introduced the task of temporal summarization, which takes as input a stream of news articles related to a particular topic, and then seeks to extract sentences describing important events as they occur.”
Trains of thought: generating information maps (2012, methodology): “In the summarization task [Nenkova and McKeown, 2012, Allan et al., 2001, Radev et al., 2005], the goal is often to summarize a corpus of texts by extracting a list of sentences.”
Query based event extraction along a timeline (2004, background): “Allan et al. [1] addressed temporal summarization of news topics by providing sentence-based summaries, where they defined precision and recall measures that capture relevance and novelty.”
Discovering Diverse and Salient Threads in Document Collections (2012, background): “Allan, Gupta, and Khandelwal (2001) introduced the task of temporal summarization , which takes a stream of news articles on a particular topic and tries to extract sentences describing important events as they occur.”
Processing Social Media Messages in Mass Emergency (2014, methodology): “Temporal text summarization refers to creating an extractive summary from a set of time-stamped documents, usually in retrospect [Allan et al. 2001; Nallapati et al. 2004; Feng and Allan 2009].”
RealTime QA: What's the Answer Right Now? (2022, background): “However, we note that most questions in R EAL T IME QA, if not all, are straightforward (e.g., single-hop questions) and a human with Internet access can easily answer them.”
Discovering evolutionary theme patterns from text: an exploration of temporal text mining (2005, methodology): “Allan and others presented a news summarization method based on ranking and selecting sentences obeying temporal order [ 1 ].”
Contextualized Word Embeddings Enhanced Event Temporal Relation Extraction for Story Understanding (2019, background): “…understanding (NLU) task with broad applications to downstream tasks such as story understanding (Charniak, 1972; Winograd, 1972; Schubert and Hwang, 2000), question answering (Pustejovsky et al., 2003a; Sa-quete et al., 2004), and text summarization (Allan et al., 2001; Georgescu et al., 2013).”
Beyond Independent Relevance (2003, methodology): “When c3 = c2, we would score documents based on p(Rel|d)p(New|d), which is essentially the scoring formula for generating temporal summaries proposed in [1], where p(Rel|d) is referred as p(Useful |d).”
Introduction to the Special Issue on Summarization (2002, background): “Research is beginning on the generation of updates on new information (Allan, Gupta, and Khandelwal 2001).”
Evolutionary timeline summarization: a balanced optimization framework via iterative substitution (2011, background): “Later they build a system to provide timelines which consist of one sentence per date, considering usefulness and novelty [1].”
Retrieval and novelty detection at the sentence level (2003, background): “That idea was addressed more satisfactorily in research on temporal summarization [3, 4], though the primary focus of their effort was to develop a useful evaluation model.”
Time-based language models (2003, background): “[7, 8]). There has also been research that exploits the temporal aspect of news streams to improve topic tracking and the detection of novel information [ 9 ].”