ANeuralAttentionModelfor.PDFVIP

A Neural Attention Model for Abstractive Sentence Summarization Alexander M. Rush Sumit Chopra Jason Weston Facebook AI Research / Facebook AI Research Facebook AI Research Harvard SEAS spchopra@ jase@ srush@ Abstract Summarization based on text extraction is inherently limited, but generation-style ab- stractive methods have proven challeng- ing to build. In this work, we propose a fully data-driven approach to abstrac- tive sentence summarization. Our method utilizes a local attention-based model that generates each word of the summary con- ditioned on the input sentence. While the model is structurally simple, it can eas- ily be trained end-to-end and scales to a large amount of training data. The model shows signi?cant performance gains on the DUC-2004 shared task compared with Figure 1: Example output of the attention-based summa- several strong baselines. rization (ABS) system. The heatmap represents a soft align- ment between the input (right) and the generated summary (top). The columns represent the distribution over the input 1 Introduction after generating each word. Summarization is an important challenge of natu- ral language understanding. The aim is to produce Lapata, 2008; Woodsend et al., 2010). These ap- a condensed representation of an input text that proaches are described in more detail in Section 6. captures the core meaning of the original. Most We instead explore a fully data-driven approach successful summarization systems utilize ex