Detailed Information on Publication Record
2022
Diverse Semantics Representation is King
GELETKA, Martin, Vojtěch KALIVODA, Michal ŠTEFÁNIK, Marek TOMA, Petr SOJKA et. al.Basic information
Original name
Diverse Semantics Representation is King
Authors
GELETKA, Martin (703 Slovakia, guarantor, belonging to the institution), Vojtěch KALIVODA (203 Czech Republic, belonging to the institution), Michal ŠTEFÁNIK (703 Slovakia, belonging to the institution), Marek TOMA (703 Slovakia, belonging to the institution) and Petr SOJKA (203 Czech Republic, belonging to the institution)
Edition
Bologna, Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum, p. 28-39, 12 pp. 2022
Publisher
CEUR.org
Other information
Language
English
Type of outcome
Stať ve sborníku
Field of Study
10201 Computer sciences, information science, bioinformatics
Country of publisher
Italy
Confidentiality degree
není předmětem státního či obchodního tajemství
Publication form
electronic version available online
References:
RIV identification code
RIV/00216224:14330/22:00126314
Organization unit
Faculty of Informatics
ISSN
Keywords (in Czech)
vyhledávání informací; odpovídání otázek; reprezentace matematiky; vyhledávání informací s včetně matematických formulí; reprezentace významu slov; slučování vyhledaných výsledků; hlasování informačních systémů; změna pořadí výsledků hledání; fúze dat; diverzita systémů; transformery
Keywords in English
information retrieval; question answering; math representations; math-aware information retrieval; word embeddings; ensembling; voting; reranking; data fusion; diversity; transformers
Tags
International impact, Reviewed
Změněno: 28/3/2023 11:45, RNDr. Pavel Šmerk, Ph.D.
Abstract
V originále
We report on the systems that the Math Information Retrieval group at Masaryk University (MIRMU) and the team of Faculty of Informatics students (MSM) prepared for task 1 (find answers) of the ARQMath lab at the CLEF conference. To study the effects of different system settings and hyperparameters, we have prototyped several diverse math-aware information retrieval (MIR) systems: both “old” inverted index-based ones and new neural ones. By ensembling the results of the “weak” individual systems into committees, we report on entailments, benefits, and drawbacks of system ensembling. We evaluated the proposed individual systems and ensembles, considering their diversity, hyperparameters, and representations used, and classified their approaches. Our prototypes have helped to understand the challenging problems of question-answering in the stem domain: the key lies in the proper representation of document semantics. Our reproducible evaluation Python library PV211-utils allows to reproduce and further advance MIR re-search.
Links
MUNI/A/1195/2021, interní kód MU |
|