The finsim-2 2021 shared task: Learning semantic similarities for the financial domain

Y Mansar, J Kang, IE Maarouf - Companion Proceedings of the Web …, 2021 - dl.acm.org
The FinSim-2 is a second edition of FinSim Shared Task on Learning Semantic Similarities
for the Financial Domain, colocated with the FinWeb workshop. FinSim-2 proposed the …

Improving word sense disambiguation with translations

Y Luan, B Hauer, L Mou, G Kondrak - Proceedings of the 2020 …, 2020 - aclanthology.org
It has been conjectured that multilingual information can help monolingual word sense
disambiguation (WSD). However, existing WSD systems rarely consider multilingual …

FinSim4-ESG shared task: Learning semantic similarities for the financial domain. extended edition to ESG insights

J Kang, I El Maarouf - Proceedings of the Fourth Workshop on …, 2022 - aclanthology.org
This paper describes FinSim4-ESG 1 shared task organized in the 4th FinNLP
workshopwhich is held in conjunction with the IJCAI-ECAI-2022 confer-enceThis year, the …

[PDF][PDF] FinSim-3: The 3rd shared task on learning semantic similarities for the financial domain

J Kang, I El Maarouf, S Bellato… - Proceedings of the Third …, 2021 - aclanthology.org
The FinSim-3 is the third edition of FinSim shared task on Learning Semantic Similarities for
the Financial Domain, held in conjunction with IJCAI 2021@ Online as part of the FinNLP …

SemEval-2020 task 2: Predicting multilingual and cross-lingual (graded) lexical entailment

G Glavaš, I Vulić, A Korhonen… - Proceedings of the …, 2020 - aclanthology.org
Lexical entailment (LE) is a fundamental asymmetric lexico-semantic relation, supporting the
hierarchies in lexical resources (eg, WordNet, ConceptNet) and applications like natural …

Ualberta at semeval 2022 task 2: Leveraging glosses and translations for multilingual idiomaticity detection

B Hauer, S Jaura, T Omarov, G Kondrak - arXiv preprint arXiv:2205.14084, 2022 - arxiv.org
We describe the University of Alberta systems for the SemEval-2022 Task 2 on multilingual
idiomaticity detection. Working under the assumption that idiomatic expressions are …

Is Less More? Quality, Quantity and Context in Idiom Processing with Natural Language Models

A Knietaite, A Allsebrook, A Minkov… - arXiv preprint arXiv …, 2024 - arxiv.org
Compositionality in language models presents a problem when processing idiomatic
expressions, as their meaning often cannot be directly derived from their individual parts …

UAlberta at SemEval-2021 Task 2: Determining sense synonymy via translations

B Hauer, H Bao, A Mallik… - Proceedings of the 15th …, 2021 - aclanthology.org
We describe the University of Alberta systems for the SemEval-2021 Word-in-Context (WiC)
disambiguation task. We explore the use of translation information for deciding whether two …

Correcting sense annotations using wordnets and translations

A Mallik, G Kondrak - Proceedings of the 12th Global Wordnet …, 2023 - aclanthology.org
Acquiring large amounts of high-quality annotated data is an open issue in word sense
disambiguation. This problem has become more critical recently with the advent of …

Toward a Concept-Based Theory of Lexical Semantics

B Hauer - 2024 - era.library.ualberta.ca
This work aims to address the lack of clear theoretical foundations in computational lexical
semantics, the sub-field of natural language processing pertaining to computing with the …