Evolutionary timeline summarization: a balanced optimization framework via iterative substitution

By Rui Yan, Xiaojun Wan, Jahna Otterbacher, Liang Kong, Xiaoming Li, Yan Zhang. 2011

204 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, methodology): “[155] evaluated methods for choosing sentences from temporally clustered documents that are relevant to a query.”
Recent advances in document summarization (2017, background): “The task can be formulated as a constrained optimization problem to select and substitute sentences that satisfies multiple requirements [199], or can be addressed in a graph ranking framework unifying inter-”
RealTime QA: What's the Answer Right Now? (2022, background): “…time, but we share the goal of dealing with novel and evolving information over time; retrieval or summarization meth-ods from these tasks (e.g., Yan et al., 2011a,b, 2012; Shou et al., 2013) can be combined with models in R EAL T IME QA to serve various time-sensitive information needs from…”
A Hierarchical Neural Autoencoder for Paragraphs and Documents (2015, background): “…coherence evaluation metrics are seldom adopted in real-world applications, and summarization researchers tend to use simple approximations like number of overlapped tokens or topic distribution similarity (e.g., (Yan et al., 2011b; Yan et al., 2011a; Celikyilmaz and Hakkani-T ¨ ur, 2011)).”
Natural Language Inference by Tree-Based Convolution and Heuristic Matching (2015, background): “NLI is in the core of natural language understanding and has wide applications in NLP, e.g., question answering (Harabagiu and Hickl, 2006) and automatic summarization (Lacatusu et al., 2006; Yan et al., 2011a; Yan et al., 2011b).”
Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System (2016, methodology): “We conducted data ﬁltering and cleaning procedures by removing extremely short replies and those of low linguistic quality such as meaningless babblings according to the evaluation framework put forward in [40, 42], so as to maintain a meaningful, high-quality conversation record.”
Discovering Diverse and Salient Threads in Document Collections (2012, methodology): “Yan et al (2011) evaluated methods for choosing sentences from temporally clustered documents that are relevant to a query.”
Trains of thought: generating information maps (2012, background): “Previous news summarization systems with structured output [Swan and Jensen, 2000, Yan et al., 2011, Allan et al., 2001] have focused mostly on timeline generation.”