REVIEW 2 cited by
Generating News Headlines with Recurrent Neural Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We describe an application of an encoder-decoder recurrent neural network with LSTM units and attention to generating headlines from the text of news articles. We find that the model is quite effective at concisely paraphrasing news articles. Furthermore, we study how the neural network decides which input words to pay attention to, and specifically we identify the function of the different neurons in a simplified attention mechanism. Interestingly, our simplified attention mechanism performs better that the more complex attention mechanism on a held out set of articles.
Forward citations
Cited by 2 Pith papers
-
Fact-Preserved Personalized News Headline Generation
FPG combines history-aware attention and contrastive learning to generate personalized news headlines that preserve article facts, reporting improved FactCC and ROUGE scores on PENS.
-
Abstractive Text Summarization for Bangla Language Using NLP and Machine Learning Approaches
A Bengali abstractive summarizer using LSTM encoder-decoder with attention is described, but no evaluation results are reported.
Discussion (0). Continue with ORCID to comment.