This age of data-driven innovation has made automated relevant and important data extraction a necessity. Automated text summarization has made it possible to extract relevant information from large amounts of data without needing any supervision. But the extracted information could seem artificial at times and that's where the abstractive summarization method tries to mimic the human way of summarizing by creating coherent summaries using novel words and sentences. Due to the difficult nature of this method, before deep learning, there hasn't been much progress. So, during this work, we have proposed an attention mechanism-based sequence-to-sequence network to generate abstractive summaries of Bengali text. We have also built our own large Bengali news dataset and applied our model on it to show indeed deep sequence-to-sequence neural networks can achieve good performance summarizing Bengali texts.