Modelling Bahdanau Attention using Election methods aided by Q-Learning

TL;DR

This paper introduces a novel approach to neural machine translation attention mechanisms by modeling them with election methods and Q-learning, resulting in faster inference without sacrificing translation quality.

Contribution

It proposes using election methods combined with reinforcement learning to model attention, reducing inference time compared to traditional Bahdanau attention.

Findings

Inference time is reduced compared to standard Bahdanau attention.

Translation quality remains comparable to traditional models.

The approach experimentally verifies the effectiveness of election-based attention modeling.

Abstract

Neural Machine Translation has lately gained a lot of "attention" with the advent of more and more sophisticated but drastically improved models. Attention mechanism has proved to be a boon in this direction by providing weights to the input words, making it easy for the decoder to identify words representing the present context. But by and by, as newer attention models with more complexity came into development, they involved large computation, making inference slow. In this paper, we have modelled the attention network using techniques resonating with social choice theory. Along with that, the attention mechanism, being a Markov Decision Process, has been represented by reinforcement learning techniques. Thus, we propose to use an election method ($k$-Borda), fine-tuned using Q-learning, as a replacement for attention networks. The inference time for this network is less than a standard Bahdanau translator, and the results of the translation are comparable. This not only experimentally verifies the claims stated above but also helped provide a faster inference.