Search Results for author:
Found 76 papers, 14 papers with code
Explainable Publication Year Prediction of Eighteenth Century Texts with the BERT Model
In this paper, we describe a BERT model trained on the Eighteenth Century Collections Online (ECCO) dataset of digitized documents.
Optical Character Recognition
Optical Character Recognition (OCR)
Fine-grained Named Entity Annotation for Finnish
We introduce a corpus with fine-grained named entity annotation for Finnish, following the OntoNotes guidelines to create a resource that is cross-lingually compatible with existing annotations for other languages.
Towards Automatic Short Answer Assessment for Finnish as a Paraphrase Retrieval Task
Automatic grouping of textual answers has the potential of allowing batch grading, but is challenging because the answers, especially longer essays, have many claims.
Explaining Classes through Stable Word Attributions
Input saliency methods have recently become a popular tool for explaining predictions of deep learning models in NLP.
Extracting Social Connections from Finnish Karelian Refugee Interviews Using LLMs
Second, we aim to evaluate several alternative ways to approach this task, comparing a number of generative models and a supervised learning approach, to gain a broader insight into the relative merits of these different approaches and their applicability in similar studies.
FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering
To test the impact of our filtering, we train GPT-2 models on both the original and the filtered datasets.
Finnish SQuAD: A Simple Approach to Machine Translation of Span Annotations
We apply a simple method to machine translate datasets with span-level annotation using the DeepL MT service and its ability to translate formatted documents.
FinGPT: Large Generative Models for a Small Language
We pursue two approaches to pretrain models: 1) we train seven monolingual models from scratch (186M to 13B parameters) dubbed FinGPT, 2) we continue the pretraining of the multilingual BLOOM model on a mix of its original training data and Finnish, resulting in a 176 billion parameter model we call BLUUMI.
Multi-CrossRE A Multi-Lingual Multi-Domain Dataset for Relation Extraction
Most research in Relation Extraction (RE) involves the English language, mainly due to the lack of multi-lingual resources.
Silver Syntax Pre-training for Cross-Domain Relation Extraction
One of the main reasons for this is the limited training size of current RE datasets: obtaining high-quality (manually annotated) data is extremely expensive and cannot realistically be repeated for each new domain.
Identifying gender bias in blockbuster movies through the lens of machine learning
The problem of gender bias is highly prevalent and well known.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
Out-of-Domain Evaluation of Finnish Dependency Parsing
The prevailing practice in the academia is to evaluate the model performance on in-domain evaluation data typically set aside from the training corpus.
Semantic Search as Extractive Paraphrase Span Detection
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 identify its paraphrase in a given document, the same modelling setup as typically used in extractive question answering.
Explaining Classes through Word Attribution
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.
Annotation Guidelines for the Turku Paraphrase Corpus
This document describes the annotation guidelines used to construct the Turku Paraphrase Corpus.
Quantitative Evaluation of Alternative Translations in a Corpus of Highly Dissimilar Finnish Paraphrases
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 non-trivial variation in translation.
Deep learning for sentence clustering in essay grading support
Essays as a form of assessment test student knowledge on a deeper level than short answer and multiple-choice questions.
Finnish Paraphrase Corpus
Out of all paraphrase pairs in our corpus 98% are manually classified to be paraphrases at least in their given context, if not in all contexts.
Towards Fully Bilingual Deep Language Modeling
Language models based on deep neural networks have facilitated great advances in natural language processing and understanding tasks in recent years.
Turku Enhanced Parser Pipeline: From Raw Text to Enhanced Graphs in the IWPT 2020 Shared Task
We present the approach of the TurkuNLP group to the IWPT 2020 shared task on Multilingual Parsing into Enhanced Universal Dependencies.
WikiBERT models: deep transfer learning for many languages
In this paper, we introduce a simple, fully automated pipeline for creating language-specific BERT models from Wikipedia data and introduce 42 new such models, most for languages up to now lacking dedicated deep neural language models.
The FISKM\"O Project: Resources and Tools for Finnish-Swedish Machine Translation and Cross-Linguistic Research
This paper presents FISKM{\"O}, a project that focuses on the development of resources and tools for cross-linguistic research and machine translation between Finnish and Swedish.
Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection
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
Deep learning-based language models pretrained on large unannotated text corpora have been demonstrated to allow efficient transfer learning for natural language processing, with recent approaches such as the transformer-based BERT model advancing the state of the art across a variety of tasks.
Morphological Tagging and Lemmatization of Albanian: A Manually Annotated Corpus and Neural Models
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 lemmatizer trained on it.
Neural Dependency Parsing of Biomedical Text: TurkuNLP entry in the CRAFT Structural Annotation Task
We present the approach taken by the TurkuNLP group in the CRAFT Structural Annotation task, a shared task on dependency parsing.
Is Multilingual BERT Fluent in Language Generation?
The multilingual BERT model is trained on 104 languages and meant to serve as a universal language model and tool for encoding sentences.
Template-free Data-to-Text Generation of Finnish Sports News
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, interpretation, insight into the game, and quotes that are not present in the official statistics.
Leveraging Text Repetitions and Denoising Autoencoders in OCR Post-correction
A common approach for improving OCR quality is a post-processing step based on models correcting misdetected characters and tokens.
Universal Lemmatizer: A Sequence to Sequence Model for Lemmatizing Universal Dependencies Treebanks
We evaluate our lemmatizer on 52 different languages and 76 different treebanks, showing that our system outperforms all latest baseline systems.
Mind the Gap: Data Enrichment in Dependency Parsing of Elliptical Constructions
In this paper, we focus on parsing rare and non-trivial constructions, in particular ellipsis.
Enhancing Universal Dependency Treebanks: A Case Study
We evaluate two cross-lingual techniques for adding enhanced dependencies to existing treebanks in Universal Dependencies.
CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Every year, the Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets.
Turku Neural Parser Pipeline: An End-to-End System for the CoNLL 2018 Shared Task
In this paper we describe the TurkuNLP entry at the CoNLL 2018 Shared Task on Multilingual Parsing from Raw Text to Universal Dependencies.
Ranked #5 on
Dependency Parsing
on Universal Dependencies
Evaluation of a Prototype System that Automatically Assigns Subject Headings to Nursing Narratives Using Recurrent Neural Network
Our aim is to allow nurses to write in a narrative manner without having to plan and structure the text with respect to sections and subject headings, instead the system should assist with the assignment of subject headings and restructuring afterwards.
Cross-Lingual Pronoun Prediction with Deep Recurrent Neural Networks v2.0
In this paper we present our system in the DiscoMT 2017 Shared Task on Crosslingual Pronoun Prediction.
TurkuNLP: Delexicalized Pre-training of Word Embeddings for Dependency Parsing
We present the TurkuNLP entry in the CoNLL 2017 Shared Task on Multilingual Parsing from Raw Text to Universal Dependencies.
CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
The Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets.
End-to-End System for Bacteria Habitat Extraction
The official evaluation shows that the joint performance of our entity detection and relation extraction models outperforms the winning team of the Shared Task by 19pp on F1-score, establishing a new top score for the task.
Detecting mentions of pain and acute confusion in Finnish clinical text
We study and compare two different approaches to the task of automatic assignment of predefined classes to clinical free-text narratives.
Universal Dependencies
Universal Dependencies (UD) is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages.
Universal Dependencies for Persian
The Persian Universal Dependency Treebank (Persian UD) is a recent effort of treebanking Persian with Universal Dependencies (UD), an ongoing project that designs unified and cross-linguistically valid grammatical representations including part-of-speech tags, morphological features, and dependency relations.
Universal Dependencies v1: A Multilingual Treebank Collection
Cross-linguistically consistent annotation is necessary for sound comparative evaluation and cross-lingual learning experiments.
An expanded evaluation of protein function prediction methods shows an improvement in accuracy
To review progress in the field, the analysis also compared the best methods participating in CAFA1 to those of CAFA2.
Quantitative Methods
Universal Stanford dependencies: A cross-linguistic typology
Revisiting the now de facto standard Stanford dependency representation, we propose an improved taxonomy to capture grammatical relations across languages, including morphologically rich ones.
Joint Morphological and Syntactic Analysis for Richly Inflected Languages
Joint morphological and syntactic analysis has been proposed as a way of improving parsing accuracy for richly inflected languages.
