Search Results for author: Veronika Laippala

Found 13 papers, 2 papers with code

Toward Multilingual Identification of Online Registers

no code implementations WS (NoDaLiDa) 2019 Veronika Laippala, Roosa Kyllönen, Jesse Egbert, Douglas Biber, Sampo Pyysalo

We consider cross- and multilingual text classification approaches to the identification of online registers (genres), i. e. text varieties with specific situational characteristics.

Multilingual text classification Multilingual Word Embeddings +1

Multilingual and Zero-Shot is Closing in on Monolingual Web Register Classification

no code implementations NoDaLiDa 2021 Samuel Rönnqvist, Valtteri Skantsi, Miika Oinonen, Veronika Laippala

This article studies register classification of documents from the unrestricted web, such as news articles or opinion blogs, in a multilingual setting, exploring both the benefit of training on multiple languages and the capabilities for zero-shot cross-lingual transfer.

Zero-Shot Cross-Lingual Transfer

Explaining Classes through Word Attribution

no code implementations31 Aug 2021 Samuel Rönnqvist, Amanda Myntti, Aki-Juhani Kyröläinen, Sampo Pyysalo, Veronika Laippala, Filip Ginter

In this work, we propose a method for explaining classes using deep learning models and the Integrated Gradients feature attribution technique by aggregating explanations of individual examples in text classification to general descriptions of the classes.

Classification Genre classification +1

From Web Crawl to Clean Register-Annotated Corpora

no code implementations LREC 2020 Veronika Laippala, Samuel R{\"o}nnqvist, Saara Hellstr{\"o}m, Juhani Luotolahti, Liina Repo, Anna Salmela, Valtteri Skantsi, Sampo Pyysalo

However, two critical steps in the development of web corpora remain challenging: the identification of clean text from source HTML and the assignment of genre or register information to the documents.

Cannot find the paper you are looking for? You can Submit a new open access paper.