Generating a summary of a given sentence.
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Automatic sentence summarization produces a shorter version of a sentence, while preserving its most important information.
The proposed method, ALONE (all word embeddings from one), constructs the embedding of a word by modifying the shared embedding with a filter vector, which is word-specific but non-trainable.
Ranked #2 on Text Summarization on DUC 2004 Task 1
We propose a contrastive attention mechanism to extend the sequence-to-sequence framework for abstractive sentence summarization task, which aims to generate a brief summary of a given source sentence.
But there is no cross-lingual parallel corpus, whose source sentence language is different to the summary language, to directly train a cross-lingual ASSUM system.
In this work we present an unsupervised approach to summarize sentences in abstractive way using Variational Autoencoder (VAE).