6467052
doi
10.5281/zenodo.6467052
oai:zenodo.org:6467052
user-connexions-h2020
user-eu
Tsikrika, Theodora
Information Technologies Institute, Centre for Research and Technology Hellas
Vrochidis, Stefanos
Information Technologies Institute, Centre for Research and Technology Hellas
Kompatsiaris, Ioannis
Information Technologies Institute, Centre for Research and Technology Hellas
M4D-MKLab/ITI-CERTH Participation in TREC Deep Learning Track 2021
Koufakis, Alexandros-Michail
Information Technologies Institute, Centre for Research and Technology Hellas
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
TREC Deep Learning
BERT
Query Expansion
IDF
<p>Our team’s (CERTH ITI M4D) goal in the TREC Deep Learning Track was to study how the Con-<br>
textualized Embedding Query Expansion (CEQE) [1] method performs in such setting and how our<br>
proposed modifications affect the performance. In particular, we examine how CEQE performs with<br>
the addition of bigrams as potential expansion terms, and how an IDF weight component affects<br>
the performance. The first run we submitted is produced by a query expansion pipeline that uses<br>
BM25 for retrieval and CEQE with the IDF modification for query expansion. The second submitted<br>
run used a modification of CEQE with the addition of bigrams as candidate expansion terms and a<br>
re-ranking step using CEDR. Our runs showed promising results, especially for Average Precision.</p>
Zenodo
2022-03-01
info:eu-repo/semantics/conferencePaper
6467051
user-connexions-h2020
user-eu
1.0
award_title=IMMERSE. INTERACT. INVESTIGATE; award_number=883293; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/883293; funder_id=00k4n6c32; funder_name=European Commission;
award_title=Fighting Crime and TerroRism with an IoT-enabled Autonomous Platform based on an Ecosystem of Advanced IntelligEnce, Operations, and InveStigation Technologies; award_number=833464; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/833464; funder_id=00k4n6c32; funder_name=European Commission;
award_title=InterCONnected NEXt-Generation Immersive IoT Platform of Crime and Terrorism DetectiON, PredictiON, InvestigatiON, and PreventiON Services; award_number=786731; award_identifiers_scheme=url; award_identifiers_identifier=https://cordis.europa.eu/projects/786731; funder_id=00k4n6c32; funder_name=European Commission;
1650896439.29697
1287723
md5:d7365483b2f849364dd2ad75d553966c
https://zenodo.org/records/6467052/files/CERTH_ITI_M4D-DL.pdf
public
10.5281/zenodo.6467051
isVersionOf
doi