Towards Abstraction from Extraction: Multiple Timescale Gated Recurrent Unit for Summarization
This addresses the problem of handling multiple compositionalities in longer texts for researchers in natural language processing, though it appears incremental.
The authors tackled abstractive summarization of scientific articles by introducing temporal hierarchies to sequence-to-sequence models, resulting in a model that trains faster and shows significant performance gains compared to conventional RNN encoder-decoder approaches.
In this work, we introduce temporal hierarchies to the sequence to sequence (seq2seq) model to tackle the problem of abstractive summarization of scientific articles. The proposed Multiple Timescale model of the Gated Recurrent Unit (MTGRU) is implemented in the encoder-decoder setting to better deal with the presence of multiple compositionalities in larger texts. The proposed model is compared to the conventional RNN encoder-decoder, and the results demonstrate that our model trains faster and shows significant performance gains. The results also show that the temporal hierarchies help improve the ability of seq2seq models to capture compositionalities better without the presence of highly complex architectural hierarchies.