/ Machine Learning

A Tensorflow implementation of Yin Wenpeng's paper Attentive Convolution at TACL

A Tensorflow implementation of Yin Wenpeng's paper Attentive Convolution at TACL

tf-attentive-conv: Attentive Convolution

A Tensorflow implementation of Yin Wenpeng's recent paper on TACL "Attentive Convolution".

This is a Tensorflow implementation of Yin Wenpeng's paper "Attentive Convolution" at TACL in 2018. Wenpeng's original code is written in Theano.

I only implement the light attentive convolution described in Sect. 3.1 of the paper. Authors argue that even this light-version AttConv outperforms some of pioneering attentive RNNs in both intra-context (context=query, i.e. self-attention) and extra-context (context!=query) settings. The following figure (from the paper) illustrates this idea:

What did I change?

Nothing big. I do add some features:

  1. add a dropout-resnet-layernorm block before the output
  2. add masking to ensure causality, so that one may use it for decoding as well.

By default these features are all disabled.

Run

Run app.py for a simple test on toy data.

GitHub