Abstract
Timeline Summarization identifies major events from a news collection and describes them following temporal order, with key dates tagged. Previous methods generally generate summaries separately for each date after they determine the key dates of events. These methods overlook the events’ intra-structures (arguments) and inter-structures (event-event connections). Following a different route, we propose to represent the news articles as an event-graph, thus the summarization becomes compressing the whole graph to its salient sub-graph. The key hypothesis is that the events connected through shared arguments and temporal order depict the skeleton of a timeline, containing events that are semantically related, temporally coherent and structurally salient in the global event graph. A time-aware optimal transport distance is then introduced for learning the compression model in an unsupervised manner. We show that our approach significantly improves on the state of the art on three real-world datasets, including two public standard benchmarks and our newly collected Timeline100 dataset.
Highlights
We propose an event graph representation along with compression to deal with the representation difficulties in global graph contextualization, scalability, and time-awareness
To obtain the optimal transport (OT): We propose a new for- minimal distance with only m events to be kept, mulation of timeline summarization, by selecting a global decision is learned to select salient but event nodes from the input graph to form a smaller diverse events
We propose a novel event graph compression framework for timeline summarization and achieve stateof-the-art on multiple real-world datasets
Summary
GPT-2 (Budzianowski and Vulic, 2019), are restricted in terms of both representation capacityTimeline summarization (Chieu and Lee, 2004; Yan et al, 2011a,b; Binh Tran et al, 2013; Tran et al, 2013, 2015; Nguyen et al, 2014; Wang et al, 2016; Martschat and Markert, 2018; Steen and Markert, 2019) aims at generating a sequence of major news events with their key dates from a large collection of related news from multiple perspectives Timeline summarization (Chieu and Lee, 2004; Yan et al, 2011a,b; Binh Tran et al, 2013; Tran et al, 2013, 2015; Nguyen et al, 2014; Wang et al, 2016; Martschat and Markert, 2018; Steen and Markert, 2019) aims at generating a sequence of major news events with their key dates from a large collection of related news from multiple perspectives The timeline summariza- (1) Event graph construction for multi-doc tion task poses several challenges to existing Natu- encoding: With state-of-the-art Information ral Language Processing (NLP) techniques: (1) In Extraction (IE) systems (Lin et al, 2020), contrast to multi-document summarization (MDS) we construct a single event graph from the dealing with tens of documents (Fabbri et al, 2019), input documents, with co-referential entities (e.g., house, mansion in Figure 1) and coreferential events (e.g., die, collapsed) merged across documents.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
