SIB text mining at TREC 2020 deep learning track

Knafou, Julien (Haute école de gestion de Genève, HES-SO // Haute Ecole Spécialisée de Suisse Occidentale ; SIB, Swiss Institute of Bioinformatics, Geneva, Switzerland ; University of Geneva, Switzerland) ; Jeffryes, Matthew (Haute école de gestion de Genève, HES-SO // Haute Ecole Spécialisée de Suisse Occidentale ; SIB, Swiss Institute of Bioinformatics, Geneva, Switzerland) ; Ferdowsi, Sohrab (Haute école de gestion de Genève, HES-SO // Haute Ecole Spécialisée de Suisse Occidentale) ; Ruch, Patrick (Haute école de gestion de Genève, HES-SO // Haute Ecole Spécialisée de Suisse Occidentale ; SIB, Swiss Institute of Bioinformatics, Geneva, Switzerland)

This second campaign of the TREC Deep Learning Track was an opportunity for us to experiment with deep neural language models reranking techniques in a realistic use case. This year’s tasks were the same as the previous edition: (1) building a reranking system and (2) building an end-to-end retrieval system. Both tasks could be completed on both a document and a passage collection. In this paper, we describe how we coupled Anserini’s information retrieval toolkit with a BERT-based classifier to build a state-of-the-art end-to-end retrieval system. Our only submission which is based on a RoBERTa large pretrained model achieves for (1)a ncdg@10 of .6558 and .6295 for passages and documents respectively and for (2) a ndcg@10 of .6614 and .6404 for passages and documents respectively.


Conference Type:
published full paper
Faculty:
Economie et Services
School:
HEG - Genève
Institute:
CRAG - Centre de Recherche Appliquée en Gestion
Subject(s):
Sciences de l'information
Publisher:
Virtual conference, 16-20 November 2020
Date:
2020-11
Virtual conference
16-20 November 2020
Pagination:
7 p.
Published in:
Proceedings of the Twenty-Ninth Text REtrieval Conference (TREC 2020)
External resources:
Appears in Collection:



 Record created 2021-07-09, last modified 2021-07-12

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)