# User Intent Classification using Memory Networks: A Comparative Analysis for a Limited Data Scenario

## TL;DR

This paper compares various models, especially memory networks, for user intent classification in app recommendation, focusing on limited data scenarios and 1-shot learning, highlighting the effectiveness of simple memory-based approaches.

## Contribution

It provides a comparative analysis of memory network architectures for multi-label intent classification with limited data, emphasizing their practical utility in dialog systems.

## Key findings

- Memory networks outperform other models in limited data settings.
- Simple non-parametric methods perform comparably with minimal training data.
- Memory networks are effective for 1-shot learning in user intent classification.

## Abstract

In this report, we provide a comparative analysis of different techniques for user intent classification towards the task of app recommendation. We analyse the performance of different models and architectures for multi-label classification over a dataset with a relative large number of classes and only a handful examples of each class. We focus, in particular, on memory network architectures, and compare how well the different versions perform under the task constraints. Since the classifier is meant to serve as a module in a practical dialog system, it needs to be able to work with limited training data and incorporate new data on the fly. We devise a 1-shot learning task to test the models under the above constraint. We conclude that relatively simple versions of memory networks perform better than other approaches. Although, for tasks with very limited data, simple non-parametric methods perform comparably, without needing the extra training data.