The Impact of Local Attention in LSTM for Abstractive Text Summarization

An attentional mechanism is very important to enhance a neural machine translation (NMT). There are two classes of attentions: global and local attentions. This paper focuses on comparing the impact of the local attention in Long Short-Term Memory (LSTM) model to generate an abstractive text summarization (ATS). Developing a model using a dataset of Amazon Fine Food Reviews and evaluating it using dataset of GloVe shows that the global attention-based model produces better ROUGE-1, where it generates more words contained in the actual summary. But, the local attention-based gives higher ROUGE-2, where it generates more pairs of words contained in the actual summary, since the mechanism of local attention considers the subset of input words instead of the whole input words.

Paper

Full text

PDF

The Impact of Local Attention in LSTM for Abstractive Text Summarization

Semantic Scholar · Computer Science · 2019

Abstract

An attentional mechanism is very important to enhance a neural machine translation (NMT). There are two classes of attentions: global and local attentions. This paper focuses on comparing the impact of the local attention in Long Short-Term Memory (LSTM) model to generate an abstractive text summarization (ATS). Developing a model using a dataset of Amazon Fine Food Reviews and evaluating it using dataset of GloVe shows that the global attention-based model produces better ROUGE-1, where it generates more words contained in the actual summary. But, the local attention-based gives higher ROUGE-2, where it generates more pairs of words contained in the actual summary, since the mechanism of local attention considers the subset of input words instead of the whole input words.

Similar papers

© 2026 NYSGPT2525 LLC