Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization
This addresses a specific issue in neural abstractive summarization, offering an incremental improvement for text generation tasks.
The paper tackled the problem of redundant repeating generation in RNN-based encoder-decoder models for abstractive summarization by jointly estimating vocabulary frequency bounds in the encoder and controlling outputs in the decoder, achieving significant improvement over a strong baseline on a benchmark.
This paper tackles the reduction of redundant repeating generation that is often observed in RNN-based encoder-decoder models. Our basic idea is to jointly estimate the upper-bound frequency of each target vocabulary in the encoder and control the output words based on the estimation in the decoder. Our method shows significant improvement over a strong RNN-based encoder-decoder baseline and achieved its best results on an abstractive summarization benchmark.