The paper introduces a novel recurrent neural network (RNN) model for abstractive sentence summarization, which generates a shorter version of a given sentence while preserving its meaning. The model, named RAS (Recurrent Attentive Summarizer), consists of a conditional RNN decoder and an encoder that uses a convolutional attention mechanism to guide the decoder's focus on relevant parts of the input sentence. The encoder computes scores over the words in the input sentence, providing a soft alignment that helps the decoder focus on the appropriate words. The model is trained end-to-end on large datasets and outperforms the state-of-the-art method on the Gigaword corpus and performs competitively on the DUC-2004 shared task. The main contributions include the novel attention-based encoder and the RNN decoder, which together improve performance compared to previous models. Experimental results show that the RAS model achieves lower perplexity and better ROUGE scores, demonstrating its effectiveness in generating fluent and meaningful summaries.The paper introduces a novel recurrent neural network (RNN) model for abstractive sentence summarization, which generates a shorter version of a given sentence while preserving its meaning. The model, named RAS (Recurrent Attentive Summarizer), consists of a conditional RNN decoder and an encoder that uses a convolutional attention mechanism to guide the decoder's focus on relevant parts of the input sentence. The encoder computes scores over the words in the input sentence, providing a soft alignment that helps the decoder focus on the appropriate words. The model is trained end-to-end on large datasets and outperforms the state-of-the-art method on the Gigaword corpus and performs competitively on the DUC-2004 shared task. The main contributions include the novel attention-based encoder and the RNN decoder, which together improve performance compared to previous models. Experimental results show that the RAS model achieves lower perplexity and better ROUGE scores, demonstrating its effectiveness in generating fluent and meaningful summaries.