Elaine Zosa's Homepage

Language processing, topic models, multilingual models, and more!

View My GitHub Profile

About me

Currently an AI Scientist for Silo AI in Helsinki. Formerly a postdoc in the Helsinki NLP Group. My research interests include topic modelling, language change, and uncertainty modelling in language tasks.

My research


I’m involved in organising SemEval2024 Task 6: SHROOM, a shared task on detecting hallucinated outputs from generative language models.

Topic models

Multilingual and Multimodal Topic Modelling with Pretrained Embeddings by Zosa, Elaine; Pivovarova, Lidia
Paper | Code

Multilingual Topic Labelling of News Topics using Ontological Mapping by Zosa, Elaine; Pivovarova, Lidia; Boggia, Michele; Ivanova, Sardana
ECIR 2022
Paper | Code

Evaluating the Robustness of Embedding-based Topic Models to OCR Noise by Zosa, Elaine; Granroth-Wilding, Mark; Mutuvi, Stephen; Doucet, Antoine.
ICADL 2021

Topic Modelling Discourse Dynamics in Historical Newspapers by Marjanen, Jani; Zosa, Elaine; Hengchen, Simon; Pivovarova, Lidia; Tolonen, Mikko
DHN 2020
Paper | Code

Multilingual Dynamic Topic Model by Zosa, Elaine; Granroth-Wilding, Mark
RANLP 2019
Paper | Code

Diachronic semantic change

The expansion of isms, 1820-1917 : Data-driven analysis of political language in digitized newspaper collections by Marjanen, Jani; Kurunmäki, Jussi Antero; Pivovarova, Lidia; Zosa, Elaine.
Journal of Data Mining and Digital Humanities, 2020.
Paper | Code

Capturing Evolution in Word Usage: Just Add More Clusters? by Martinc, Matej; Montariol, Syrielle; Zosa, Elaine; Pivovarova, Lidia.
WWW ‘20: Companion Proceedings of the Web Conference 2020
Paper | Code

Headline generation

Effectiveness of Data Augmentation and Pretraining for Improving Neural Headline Generation in Low-Resource Settings by Martinc, Matej; Montariol, Syrielle; Pivovarova, Lidia; Zosa, Elaine
LREC 2022
Paper | Code

Multilingual news similarity

EMBEDDIA at SemEval-2022 Task 8: Investigating Sentence, Image, and Knowledge Graph Representations for Multilingual News Article Similarity by Zosa, Elaine; Boros, Emanuela; Koloski, Boshko; Pivovarova, Lidia
SemEval 2022
Paper | Code


The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens
Genome Biology 20, 244 (2019)


NewsEye (2018-2022) EMBEDDIA (2019-2022)

I’m on LinkedIn!

Google Scholar