Zero-shot, One Kill: BERT for Neural Information Retrieval

Zero-shot, One Kill: BERT for Neural Information Retrieval

[Background]: The advent of bidirectional encoder representation from trans- formers (BERT) language models (Devlin et al., 2018) and MS Marco, a large scale human-annotated dataset for machine reading comprehension (Bajaj et al., 2016) that made publicly available, led the field of information retr...

Full description

Bibliographic Details
Main Author: Efes, Stergios
Format: Others
Language:English
Published: Uppsala universitet, Institutionen för lingvistik och filologi 2021
Subjects:
neural information retrieval
passage ranking
weak supervision
question answering
passage reranking
BERT
transfer-learning in IR
zero-shot IR
passage-retrieval
BERT for passage-retrieval
MS Marco
information retrieval
neural IR
Language Technology (Computational Linguistics)
Språkteknologi (språkvetenskaplig databehandling)
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-444835

Internet

http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-444835

Similar Items