A Temporally Sensitive Submodularity Framework for Timeline Summarization

Abstract

Timeline summarization (TLS) creates an overview of long-running events via dated daily summaries for the most important dates. TLS differs from standard multi-document summarization (MDS) in the importance of date selection, interdependencies between summaries of different dates and by having very short summaries compared to the number of corpus documents. However, we show that MDS optimization models using submodular functions can be adapted to yield wellperforming TLS models by designing objective functions and constraints that model the temporal dimension inherent in TLS. Importantly, these adaptations retain the elegance and advantages of the original MDS models (clear separation of features and inference, performance guarantees and scalability, little need for supervision) that current TLS-specific models lack. An open-source implementation of the framework and all models described in this paper is available online. 1 16 Predecessors of this task were the update and temporal summarization tasks (Aslam et al., 2015)

Abstractive Timeline Summarization

“…1. We introduce the first abstractive system for TLS and show that it outperforms current ex-tractive TLS systems such as Martschat and Markert (2018) when the input corpora are large with low compression rate. 1 2.…”

“…While both TLS and Multi-Document Summarization (MDS) generate summaries from multiple input documents, there are substantial differences between the two tasks. Specifically, Martschat and Markert (2018) Figure 1: A graphical overview of our system. We can see that not all clusters are included in the timeline.…”

“…We construct A using TF-IDF vector cosine similarity between the input sentences, which has been shown to be a useful similarity metric for TLS (Martschat and Markert, 2018;Chieu and Lee, 2004). However, sentences in the same cluster should not only be similar but also describe the same dates.…”

“…We determine the importance dimp(d) of a date d by counting how often it is mentioned in the input (Martschat and Markert, 2018). The score f date of a sentence g is f date (g) = dimp(date(g)).…”

“…6 Chieu is a reimplementation of Chieu and Lee (2004), which uses the average cosine similarity of a sentence in a time-window around its date to determine importance and greedy selection. This system is often seen as a baseline for TLS systems (Martschat and Markert, 2018;Tran et al, 2015).…”