Liina Repo


2022

pdf
Explainable Publication Year Prediction of Eighteenth Century Texts with the BERT Model
Iiro Rastas | Yann Ciarán Ryan | Iiro Tiihonen | Mohammadreza Qaraei | Liina Repo | Rohit Babbar | Eetu Mäkelä | Mikko Tolonen | Filip Ginter
Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change

In this paper, we describe a BERT model trained on the Eighteenth Century Collections Online (ECCO) dataset of digitized documents. The ECCO dataset poses unique modelling challenges due to the presence of Optical Character Recognition (OCR) artifacts. We establish the performance of the BERT model on a publication year prediction task against linear baseline models and human judgement, finding the BERT model to be superior to both and able to date the works, on average, with less than 7 years absolute error. We also explore how language change over time affects the model by analyzing the features the model uses for publication year predictions as given by the Integrated Gradients model explanation method.

2021

pdf
Beyond the English Web: Zero-Shot Cross-Lingual and Lightweight Monolingual Classification of Registers
Liina Repo | Valtteri Skantsi | Samuel Rönnqvist | Saara Hellström | Miika Oinonen | Anna Salmela | Douglas Biber | Jesse Egbert | Sampo Pyysalo | Veronika Laippala
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop

We explore cross-lingual transfer of register classification for web documents. Registers, that is, text varieties such as blogs or news are one of the primary predictors of linguistic variation and thus affect the automatic processing of language. We introduce two new register-annotated corpora, FreCORE and SweCORE, for French and Swedish. We demonstrate that deep pre-trained language models perform strongly in these languages and outperform previous state-of-the-art in English and Finnish. Specifically, we show 1) that zero-shot cross-lingual transfer from the large English CORE corpus can match or surpass previously published monolingual models, and 2) that lightweight monolingual classification requiring very little training data can reach or surpass our zero-shot performance. We further analyse classification results finding that certain registers continue to pose challenges in particular for cross-lingual transfer.

2020

pdf
From Web Crawl to Clean Register-Annotated Corpora
Veronika Laippala | Samuel Rönnqvist | Saara Hellström | Juhani Luotolahti | Liina Repo | Anna Salmela | Valtteri Skantsi | Sampo Pyysalo
Proceedings of the 12th Web as Corpus Workshop

The web presents unprecedented opportunities for large-scale collection of text in many languages. 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. In this paper, we evaluate a multilingual approach to this end. Our starting points are the Swedish and French Common Crawl datasets gathered for the 2017 CoNLL shared task, particularly the URLs. We 1) fetch HTML pages based on the URLs and run boilerplate removal, 2) train a classifier to further clean out undesired text fragments, and 3) annotate text registers. We compare boilerplate removal against the CoNLL texts, and find an improvement. For the further cleaning of undesired material, the best results are achieved using Multilingual BERT with monolingual fine-tuning. However, our results are promising also in a cross-lingual setting, without fine-tuning on the target language. Finally, the register annotations show that most of the documents belong to a relatively small set of registers, which are relatively similar in the two languages. A number of additional flags in the annotation are, however, necessary to reflect the wide range of linguistic variation associated with the documents.