# Qwant Research @DEFT 2019: Document matching and information retrieval using clinical cases

## TL;DR

This paper presents Qwant Research's methods for clinical case matching and information extraction in French, utilizing language models, neural networks, and linguistic analysis to improve semantic similarity assessment and extraction accuracy.

## Contribution

The paper introduces novel approaches combining language models, neural networks, and linguistic analysis for clinical case matching and information extraction in French.

## Key findings

- Improved semantic similarity results with optimized preprocessing and matching techniques.
- Achieved high accuracy in clinical information extraction.
- Demonstrated effectiveness of neural networks and linguistic analysis approaches.

## Abstract

This paper reports on Qwant Research contribution to tasks 2 and 3 of the DEFT 2019's challenge, focusing on French clinical cases analysis. Task 2 is a task on semantic similarity between clinical cases and discussions. For this task, we propose an approach based on language models and evaluate the impact on the results of different preprocessings and matching techniques. For task 3, we have developed an information extraction system yielding very encouraging results accuracy-wise. We have experimented two different approaches, one based on the exclusive use of neural networks, the other based on a linguistic analysis.