A Dynamic Evolutionary Framework for Timeline Generation based on Distributed Representations
Dongyun Liang, Guohua Wang, Jing Nie

TL;DR
This paper introduces a novel unsupervised dynamic framework utilizing distributed representations for timeline generation from timestamped web documents, effectively capturing evolving topics and outperforming existing methods.
Contribution
A new evolutionary timeline generation framework based on distributed representations that dynamically finds the most likely sequence of summaries, improving coherence and relevance.
Findings
Outperforms various competitive baselines
Achieves state-of-the-art performance in timeline generation
Demonstrates feasibility of unsupervised summarization approach
Abstract
Given the collection of timestamped web documents related to the evolving topic, timeline summarization (TS) highlights its most important events in the form of relevant summaries to represent the development of a topic over time. Most of the previous work focuses on fully-observable ranking models and depends on hand-designed features or complex mechanisms that may not generalize well. We present a novel dynamic framework for evolutionary timeline generation leveraging distributed representations, which dynamically finds the most likely sequence of evolutionary summaries in the timeline, called the Viterbi timeline, and reduces the impact of events that irrelevant or repeated to the topic. The assumptions of the coherence and the global view run through our model. We explore adjacent relevance to constrain timeline coherence and make sure the events evolve on the same topic with a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Advanced Text Analysis Techniques
