Articles

AbstractThe need for large corpora raw corpora has dramatically increased in recent years with the introduction of transfer learning and semi-supervised learning methods to Natural Language Processing. And while there have been some recent attempts to manually curate the amount of data necessary to train large language models, the main …...

AbstractModern Natural Language Processing relies on the availability of annotated corpora for training and evaluating models. Such resources are scarce, especially for specialized domains in languages other than English. In particular, there are very few resources for semantic similarity in the clinical domain in French. This can be useful for …...

AbstractThe disambiguation of causative-passive homonymy (CPH) is potentially tricky for machines, as the causative and the passive are not distinguished by the sentences’ syntactic structure. By transforming CPH disambiguation to a challenging natural language inference (NLI) task, we present the first Chinese Adversarial NLI challenge set (CANLI). We show that …...

AbstractWe evaluate two popular neural cognate generation models’ robustness to several types of human-plausible noise (deletion, duplication, swapping, and keyboard errors, as well as a new type of error, phonological errors). We find that duplication and phonological substitution is least harmful, while the other types of errors are harmful. We …...

AbstractThe evaluation of Handwritten Text Recognition (HTR) models during their development is straightforward: because HTR is a supervised problem, the usual data split into training, validation, and test data sets allows the evaluation of models in terms of accuracy or error rates. However, the evaluation process becomes tricky as soon …...

AbstractNoisy labels in training data present a challenging issue in classification tasks, misleading a model towards incorrect decisions during training. In this paper, we propose the use of a linear noise model to augment pre-trained language models to account for label noise in fine-tuning. We test our approach in a …...

AbstractIn recent years there have been considerable advances in pre-trained language models, where non-English language versions have also been made available. Due to their increasing use, many lightweight versions of these models (with reduced parameters) have also been released to speed up training and inference times. However, versions of these …...

AbstractOpen cloze tests are a standard type of exercise where examinees must complete a text by filling in the gaps without any given options to choose from. This paper presents the Cambridge Exams Publishing Open Cloze (CEPOC) dataset, a collection of open cloze tests from world-renowned English language proficiency examinations. …...

AbstractAccess to large pre-trained models of varied architectures, in many different languages, is central to the democratization of NLP. We introduce PAGnol, a collection of French GPT models. Using scaling laws, we efficiently train PAGnol-XL (1.5B parameters) with the same computational budget as CamemBERT, a model 13 times smaller. PAGnol-XL …...

AbstractThis article presents the first results of the CLARIAH-funded project ‘Patterns in Translation: Using Colibri Core for the Syriac Bible’ (PaTraCoSy). This project seeks to use Colibri Core to detect translation patterns in the Peshitta, the Syriac translation of the Hebrew Bible. We first describe how we constructed word and …...

AbstractDiacritics restoration has become a ubiquitous task in the Latin-alphabet-based English-dominated Internet language environment. In this paper, we describe a small footprint 1D dilated convolution-based approach which operates on a character-level. We find that neural networks based on 1D dilated convolutions are competitive alternatives to solutions based on recurrent neural …...

AbstractAutomatic de-identification is a cost-effective and straightforward way of removing large amounts of personally identifiable information from large and sensitive corpora. However, these systems also introduce errors into datasets due to their imperfect precision. These corruptions of the data may negatively impact the utility of the de-identified dataset. This paper …...

AbstractWord embedding models have become commonplace in a wide range of NLP applications. In order to train and use the best possible models, accurate evaluation is needed. For extrinsic evaluation of word embedding models, analogy evaluation sets have been shown to be a good quality estimator. We introduce an Icelandic …...

AbstractEvent identification in technical logbooks poses challenges given the limited logbook data available in specific technical domains, the large set of possible classes, and logbook entries typically being in short form and non-standard technical language. Technical logbook data typically has both a domain, the field it comes from (e.g., automotive), …...

AbstractThe performance of Machine Translation (MT) systems varies significantly with inputs of diverging features such as topics, genres, and surface properties. Though there are many MT evaluation metrics that generally correlate with human judgments, they are not directly useful in identifying specific shortcomings of MT systems. In this demo, we …...

AbstractThis paper describes how idiom-related language resources, collected through a crowdsourcing experiment carried out by means of Dodiom, a Game-with-a-purpose, have been analysed by language experts. The paper focuses on the criteria adopted for the data annotation and evaluation process. The main scope of this project is, indeed, the evaluation …...

AbstractTransformer models have achieved significant improvements in multiple downstream tasks in recent years. One of the main contributions of Transformers is their ability to create new representations for out-of-vocabulary (OOV) words. In this paper, we have evaluated three categories of OOVs: (A) new domain-specific terms (e.g., “eucaryote’” in microbiology), (B) …...

AbstractIn this work, we explore the relationship between depression and manifestations of happiness in social media. While the majority of works surrounding depression focus on symptoms, psychological research shows that there is a strong link between seeking happiness and being diagnosed with depression. We make use of Positive-Unlabeled learning paradigm …...

AbstractThe quality of artificially generated texts has considerably improved with the advent of transformers. The question of using these models to generate learning data for supervised learning tasks naturally arises, especially when the original language resource cannot be distributed, or when it is small. In this article, this question is …...

AbstractSocial media posts containing hate speech are reproduced and redistributed at an accelerated pace, reaching greater audiences at a higher speed. We present a machine learning system for automatic detection of hate speech in Turkish, along with a hate speech dataset consisting of tweets collected in two separate domains. We …...