Pattern recognition (psychology)

Automatic summarization

Biology

Operating system

Algorithm

Encoder

Encoding (memory)

Philosophy

Paleontology

Artificial intelligence

Semantics (computer science)

Repetition (rhetorical device)

Programming language

Natural language processing

Sequence (biology)

Context (archaeology)

Computer science

Linguistics

Speech recognition

Genetics

Decoding methods

Convolutional neural network

In neural abstractive summarization, the conventional sequence-to-sequence (seq2seq) model often suffers from repetition and semantic irrelevance. To tackle the problem, we propose a global encoding framework, which controls the information flow from the encoder to the decoder based on the global information of the source context. It consists of a convolutional gated unit to perform global encoding to improve the representations of the source-side information. Evaluations on the LCSTS and the English Gigaword both demonstrate that our model outperforms the baseline models, and the analysis shows that our model is capable of generating summary of higher quality and reducing repetition.

Global Encoding for Abstractive Summarization