# HFL-RC System at SemEval-2018 Task 11: Hybrid Multi-Aspects Model for Commonsense Reading Comprehension

## TL;DR

This paper introduces the HMA model, a neural network that mimics human intuition by analyzing multiple aspects through attention mechanisms, achieving state-of-the-art results in commonsense reading comprehension at SemEval-2018.

## Contribution

The paper presents a novel Hybrid Multi-Aspects neural network that improves performance in commonsense reading comprehension by integrating multiple attention-based analyses.

## Key findings

- Achieved 84.13% accuracy on the SemEval-2018 Task 11 leaderboard.
- Outperformed baseline systems significantly.
- Demonstrated effectiveness of multi-aspect attention in comprehension tasks.

## Abstract

This paper describes the system which got the state-of-the-art results at SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge. In this paper, we present a neural network called Hybrid Multi-Aspects (HMA) model, which mimic the human's intuitions on dealing with the multiple-choice reading comprehension. In this model, we aim to produce the predictions in multiple aspects by calculating attention among the text, question and choices, and combine these results for final predictions. Experimental results show that our HMA model could give substantial improvements over the baseline system and got the first place on the final test set leaderboard with the accuracy of 84.13%.