# Multitask Learning with Deep Neural Networks for Community Question Answering

## TL;DR

This paper presents a deep neural network that jointly learns three community question answering tasks, improving accuracy and convergence without manual feature engineering, and approaching state-of-the-art results.

## Contribution

The authors introduce a multitask deep neural network that encodes questions and comments into shared representations for multiple cQA tasks, enhancing performance.

## Key findings

- Higher accuracy than individual models
- Faster convergence rates
- Competitive with feature-engineered methods

## Abstract

In this paper, we developed a deep neural network (DNN) that learns to solve simultaneously the three tasks of the cQA challenge proposed by the SemEval-2016 Task 3, i.e., question-comment similarity, question-question similarity and new question-comment similarity. The latter is the main task, which can exploit the previous two for achieving better results. Our DNN is trained jointly on all the three cQA tasks and learns to encode questions and comments into a single vector representation shared across the multiple tasks. The results on the official challenge test set show that our approach produces higher accuracy and faster convergence rates than the individual neural networks. Additionally, our method, which does not use any manual feature engineering, approaches the state of the art established with methods that make heavy use of it.