Position-aware Self-attention with Relative Positional Encodings for Slot Filling
This work addresses relation extraction for natural language processing, representing an incremental improvement through a novel attention-based architecture.
The paper tackles relation extraction by applying self-attention with relative positional encodings to slot filling, achieving improved performance over previous state-of-the-art methods on the TACRED dataset.
This paper describes how to apply self-attention with relative positional encodings to the task of relation extraction. We propose to use the self-attention encoder layer together with an additional position-aware attention layer that takes into account positions of the query and the object in the sentence. The self-attention encoder also uses a custom implementation of relative positional encodings which allow each word in the sentence to take into account its left and right context. The evaluation of the model is done on the TACRED dataset. The proposed model relies only on attention (no recurrent or convolutional layers are used), while improving performance w.r.t. the previous state of the art.