# Sequence to Sequence Learning for Query Expansion

## TL;DR

This paper explores the application of sequence-to-sequence neural networks for query expansion in information retrieval and question-answering, using open datasets and sentence-embedding techniques to train and evaluate the model.

## Contribution

It introduces a novel approach of using sequence-to-sequence models for query expansion, filling a gap in IR and QA literature with a custom training set derived from sentence embeddings.

## Key findings

- Sequence-to-sequence models can learn expanding relations in embedding space.
- The approach demonstrates potential for improving query expansion techniques.
- Open datasets and sentence embeddings are effective for training query expansion models.

## Abstract

Using sequence to sequence algorithms for query expansion has not been explored yet in Information Retrieval literature nor in Question-Answering's. We tried to fill this gap in the literature with a custom Query Expansion engine trained and tested on open datasets. Starting from open datasets, we built a Query Expansion training set using sentence-embeddings-based Keyword Extraction. We therefore assessed the ability of the Sequence to Sequence neural networks to capture expanding relations in the words embeddings' space.