Extractive Summarization with SWAP-NET: Sentences and Words from Alternating Pointer Networks

Abstract

We present a new neural sequence-tosequence model for extractive summarization called SWAP-NET (Sentences and Words from Alternating Pointer Networks). Extractive summaries comprising a salient subset of input sentences, often also contain important key words. Guided by this principle, we design SWAP-NET that models the interaction of key words and salient sentences using a new twolevel pointer network based architecture. SWAP-NET identifies both salient sentences and key words in an input document, and then combines them to form the extractive summary. Experiments on large scale benchmark corpora demonstrate the efficacy of SWAP-NET that outperforms state-of-the-art extractive summarizers.

DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization

“…Traditional summarization methods usually depend on manual rules and expert knowledge, such as the expanding rules of noisy-channel models (Daumé III and Marcu 2002;Knight and Marcu 2002), objectives and constraints of Integer Linear Programming (ILP) models (Woodsend and Lapata 2012; Parveen, Ramsl, and Strube 2015;Bing et al 2015), human-engineered features of some sequence classification methods (Shen et al 2007), and so on. Deep learning models can learn continuous features automatically and have made substantial progress in multiple NLP areas.…”

“…(Narayan, Cohen, and Lapata 2018) conceptualizes extractive summarization as a sentence ranking task and optimizes the ROUGE evaluation metric through an RL objective. (Jadhav and Rajan 2018) models the interaction of keywords and salient sentences using a two-level pointer network and combines them to generate the extractive summary.…”

“…extracted, and many abstractive models (See, Liu, and Manning 2017;Jadhav and Rajan 2018) are developed based on the encoder-decoder framework that encodes a document and decodes its summary. These existing neural summarizers mostly aim to build an end-to-end mapping from the input document to its summary.…”

“…To alleviate these problems, we propose a neural extractive summarizer named DeepChannel, which estimates salience for guiding the extraction procedure instead of learning an end-to-end mapping. DeepChannel is inspired by the noisy-channel (Knight and Marcu 2002;Daumé III and Marcu 2002), a probabilistic approach for sentence-level and document-level compression. Given an input document D, the noisy-channel model aims to find an optimal summary S that maximizes P (S|D).…”

Attention Optimization for Abstractive Document Summarization

“…The exploration on document summarization can be broadly divided into extractive and abstractive summarization. The extractive methods (Nallapati et al, 2017;Jadhav and Rajan, 2018;Shi Article: poundland has been been forced to pull decorative plastic easter eggs from their shelves over fears children may choke -because they look like cadbury mini eggs . trading standards officials in buckinghamshire and surrey raised the alarm over the chinese made decorations , as they were ' likely to contravene food imitation safety rules ' .…”