MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chaybouti, Sofian, Saghe, Achraf, Shabou, Aymen
Format: Preprint
Veröffentlicht: 2020
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915195544141824
author Chaybouti, Sofian
Saghe, Achraf
Shabou, Aymen
author_facet Chaybouti, Sofian
Saghe, Achraf
Shabou, Aymen
contents This paper introduces MIX, a multi-task deep learning approach to solve open-ended question-answering. First, we design our system as a multi-stage pipeline of 3 building blocks: a BM25-based Retriever to reduce the search space, a RoBERTa-based Scorer, and an Extractor to rank retrieved paragraphs and extract relevant text spans, respectively. Eventually, we further improve the computational efficiency of our system to deal with the scalability challenge: thanks to multi-task learning, we parallelize the close tasks solved by the Scorer and the Extractor. Our system is on par with state-of-the-art performances on the squad-open benchmark while being simpler conceptually.
format Preprint
id arxiv_https___arxiv_org_abs_2012_09766
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering
Chaybouti, Sofian
Saghe, Achraf
Shabou, Aymen
Computation and Language
I.2.7
This paper introduces MIX, a multi-task deep learning approach to solve open-ended question-answering. First, we design our system as a multi-stage pipeline of 3 building blocks: a BM25-based Retriever to reduce the search space, a RoBERTa-based Scorer, and an Extractor to rank retrieved paragraphs and extract relevant text spans, respectively. Eventually, we further improve the computational efficiency of our system to deal with the scalability challenge: thanks to multi-task learning, we parallelize the close tasks solved by the Scorer and the Extractor. Our system is on par with state-of-the-art performances on the squad-open benchmark while being simpler conceptually.
title MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering
topic Computation and Language
I.2.7
url https://arxiv.org/abs/2012.09766