Modelling Events through Memory-based, Open-IE Patterns for Abstractive Summarization

Abstract

Abstractive text summarization of news requires a way of representing events, such as a collection of pattern clusters in which every cluster represents an event (e.g., marriage) and every pattern in the cluster is a way of expressing the event (e.g., X married Y, X and Y tied the knot). We compare three ways of extracting event patterns: heuristics-based, compressionbased and memory-based. While the former has been used previously in multidocument abstraction, the latter two have never been used for this task. Compared with the first two techniques, the memorybased method allows for generating significantly more grammatical and informative sentences, at the cost of searching a vast space of hundreds of millions of parse trees of known grammatical utterances. To this end, we introduce a data structure and a search method that make it possible to efficiently extrapolate from every sentence the parse sub-trees that match against any of the stored utterances.

Abstractive Multi-Document Summarization via Phrase Selection and Merging

“…Researchers also explored some variants of the typical MDS setting, such as query-chain focused summarization that combines aspects of update summarization and query-focused summarization (Baumel et al, 2014), and hierarchical summarization that scales up MDS to summarize a large set of documents (Christensen et al, 2014). A data-driven method for mining sentence structures on large news archive was proposed and utilized to summarize unseen news events (Pighin et al, 2014). Moreover, some works (Liu et al, 2012;Kågebäck et al, 2014;Denil et al, 2014;Cao et al, 2015) utilized deep learning techniques to tackle some summarization tasks.…”

Idest: Learning a Distributed Representation for Event Patterns

“…• Sentence compression, which takes as input the original sentence and the entities of interest and produces a shorter version of the sentence that still includes the entities (Pighin et al, 2014). …”

“…Event patterns and Open-IE Although some earlier work uses the temporal dimension of text as filters to improve precision of relational pattern clusters, NEWSSPIKE (Zhang & Weld, 2013) and HEADY (Alfonseca et al, 2013;Pighin et al, 2014) fully rely on it as its main supervision signal. In order to compare the two approaches, we will start by defining some terms:…”

Abstractive Multi-Document Summarization Based on Semantic Link Network

“…(2) Information extraction-based approaches ( [33], [34], [35], [36]), which firstly extract important information units, such as Subject-Verb-Object triples, from documents and then generate new descriptions for them based on manually designed templates or patterns learned from corpus. (3) Paraphrasing based approaches ( [37], [38], [39], [40]), which paraphrase the original sentences with sentence rewriting rules, such as sentence compression, phrases substitution and co-reference resolution, to generate more informative and concise summaries.…”