457 citations · 1k across the 21 of their papers we have counts for
21 papers · 1 filter
FinGPT: Large Generative Models for a Small Language
Risto Luukkonen, Ville Komulainen, Jouni Luoma +18
Large language models (LLMs) excel in many tasks in NLP and beyond, but most open models have very limited coverage of smaller languages and LLM work tends to focus on languages wh…
Silver Syntax Pre-training for Cross-Domain Relation Extraction
Elisa Bassignana, Filip Ginter, Sampo Pyysalo +2
Relation Extraction (RE) remains a challenging task, especially when considering realistic out-of-domain evaluations. One of the main reasons for this is the limited training size…
Multi-CrossRE A Multi-Lingual Multi-Domain Dataset for Relation Extraction
Elisa Bassignana, Filip Ginter, Sampo Pyysalo +2
Most research in Relation Extraction (RE) involves the English language, mainly due to the lack of multi-lingual resources. We propose Multi-CrossRE, the broadest multi-lingual dat…
Identifying gender bias in blockbuster movies through the lens of machine learning
Muhammad Junaid Haris, Aanchal Upreti, Melih Kurtaran +3
The problem of gender bias is highly prevalent and well known. In this paper, we have analysed the portrayal of gender roles in English movies, a medium that effectively influences…
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran +74
Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using…
Out-of-Domain Evaluation of Finnish Dependency Parsing
Jenna Kanerva, Filip Ginter
The prevailing practice in the academia is to evaluate the model performance on in-domain evaluation data typically set aside from the training corpus. However, in many real world…
Semantic Search as Extractive Paraphrase Span Detection
Jenna Kanerva, Hanna Kitti, Li-Hsin Chang +3
In this paper, we approach the problem of semantic search by framing the search task as paraphrase span detection, i.e. given a segment of text as a query phrase, the task is to id…
Explaining Classes through Word Attribution
Samuel Rönnqvist, Amanda Myntti, Aki-Juhani Kyröläinen +3
In recent years, several methods have been proposed for explaining individual predictions of deep learning models, yet there has been little study of how to aggregate these predict…
Annotation Guidelines for the Turku Paraphrase Corpus
Jenna Kanerva, Filip Ginter, Li-Hsin Chang +8
This document describes the annotation guidelines used to construct the Turku Paraphrase Corpus. These guidelines were developed together with the corpus annotation, revising and e…
Quantitative Evaluation of Alternative Translations in a Corpus of Highly Dissimilar Finnish Paraphrases
Li-Hsin Chang, Sampo Pyysalo, Jenna Kanerva +1
In this paper, we present a quantitative evaluation of differences between alternative translations in a large recently released Finnish paraphrase corpus focusing in particular on…
Deep learning for sentence clustering in essay grading support
Li-Hsin Chang, Iiro Rastas, Sampo Pyysalo +1
Essays as a form of assessment test student knowledge on a deeper level than short answer and multiple-choice questions. However, the manual evaluation of essays is time- and labor…
Finnish Paraphrase Corpus
Jenna Kanerva, Filip Ginter, Li-Hsin Chang +7
In this paper, we introduce the first fully manually annotated paraphrase corpus for Finnish containing 53,572 paraphrase pairs harvested from alternative subtitles and news headin…
Towards Fully Bilingual Deep Language Modeling
Li-Hsin Chang, Sampo Pyysalo, Jenna Kanerva +1
Language models based on deep neural networks have facilitated great advances in natural language processing and understanding tasks in recent years. While models covering a large…
WikiBERT models: deep transfer learning for many languages
Sampo Pyysalo, Jenna Kanerva, Antti Virtanen +1
Deep neural language models such as BERT have enabled substantial recent advances in many natural language processing tasks. Due to the effort and computational cost involved in th…
Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection
Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter +6
Universal Dependencies is an open community effort to create cross-linguistically consistent treebank annotation for many languages within a dependency-based lexicalist framework.…
Multilingual is not enough: BERT for Finnish
Antti Virtanen, Jenna Kanerva, Rami Ilo +5
Deep learning-based language models pretrained on large unannotated text corpora have been demonstrated to allow efficient transfer learning for natural language processing, with r…
Morphological Tagging and Lemmatization of Albanian: A Manually Annotated Corpus and Neural Models
Nelda Kote, Marenglen Biba, Jenna Kanerva +2
In this paper, we present the first publicly available part-of-speech and morphologically tagged corpus for the Albanian language, as well as a neural morphological tagger and lemm…
Is Multilingual BERT Fluent in Language Generation?
Samuel Rönnqvist, Jenna Kanerva, Tapio Salakoski +1
The multilingual BERT model is trained on 104 languages and meant to serve as a universal language model and tool for encoding sentences. We explore how well the model performs on…
Template-free Data-to-Text Generation of Finnish Sports News
Jenna Kanerva, Samuel Rönnqvist, Riina Kekki +2
News articles such as sports game reports are often thought to closely follow the underlying game statistics, but in practice they contain a notable amount of background knowledge,…
Leveraging Text Repetitions and Denoising Autoencoders in OCR Post-correction
Kai Hakala, Aleksi Vesanto, Niko Miekka +2
A common approach for improving OCR quality is a post-processing step based on models correcting misdetected characters and tokens. These models are typically trained on aligned pa…
Universal Lemmatizer: A Sequence to Sequence Model for Lemmatizing Universal Dependencies Treebanks
Jenna Kanerva, Filip Ginter, Tapio Salakoski
In this paper we present a novel lemmatization method based on a sequence-to-sequence neural network architecture and morphosyntactic context representation. In the proposed method…