Long Short-Term Attention
This addresses the problem of focusing on important information in sequences for machine learning practitioners, but it is incremental as it builds on existing LSTM and attention concepts.
The paper tackles the lack of attention mechanisms in sequence models like LSTM by introducing Long Short-Term Attention (LSTA), which integrates attention into LSTM cells, and shows that LSTA outperforms LSTM and related models on sequence learning tasks.
Attention is an important cognition process of humans, which helps humans concentrate on critical information during their perception and learning. However, although many machine learning models can remember information of data, they have no the attention mechanism. For example, the long short-term memory (LSTM) network is able to remember sequential information, but it cannot pay special attention to part of the sequences. In this paper, we present a novel model called long short-term attention (LSTA), which seamlessly integrates the attention mechanism into the inner cell of LSTM. More than processing long short term dependencies, LSTA can focus on important information of the sequences with the attention mechanism. Extensive experiments demonstrate that LSTA outperforms LSTM and related models on the sequence learning tasks.