This paper introduces a comprehensive collection of NLP resources for Emakhuwa, Mozambique’s most widely spoken language. The resources include the first manually translated news bitext corpus between Portuguese and Emakhuwa, news topic classification datasets, and monolingual data. We detail the process and challenges of acquiring this data and present benchmark results for machine translation and news topic classification tasks. Our evaluation examines the impact of different data types—originally clean text, post-corrected OCR, and back-translated data—and the effects of fine-tuning from pre-trained models, including those focused on African languages.Our benchmarks demonstrate good performance in news topic classification and promising results in machine translation. We fine-tuned multilingual encoder-decoder models using real and synthetic data and evaluated them on our test set and the FLORES evaluation sets. The results highlight the importance of incorporating more data and potential for future improvements.All models, code, and datasets are available in the https://huggingface.co/LIACC repository under the CC BY 4.0 license.

We present a new dataset, , that provides valuable insight for advancing discourse analysis of parliamentary debates in Portuguese. This is achieved by processing the open-access information available at the official Portuguese Parliament website and scraping the information from the debate minutes’ PDFs contained therein. Our dataset includes interventions from 547 different deputies of all major Portuguese parties, from 736 legislative initiatives spanning five legislatures from 2005 to 2021. We present a statistical analysis of the dataset compared to other publicly available Portuguese parliamentary debate corpora. Finally, we provide baseline performance analysis for voting behaviour classification.

To foster the neural encoding of Portuguese, this paper contributes foundation encoder models that represent an expansion of the still very scarce ecosystem of large language models specifically developed for this language that are fully open, in the sense that they are open source and openly distributed for free under an open license for any purpose, thus including research and commercial usages. Like most languages other than English, Portuguese is low-resourced in terms of these foundational language resources, there being the inaugural 900 million parameter Albertina and 335 million Bertimbau. Taking this couple of models as an inaugural set, we present the extension of the ecosystem of state-of-the-art open encoders for Portuguese with a larger, top performance-driven model with 1.5 billion parameters, and a smaller, efficiency-driven model with 100 million parameters. While achieving this primary goal, further results that are relevant for this ecosystem were obtained as well, namely new datasets for Portuguese based on the SuperGLUE benchmark, which we also distribute openly.

As part of the Open Language Data Initiative shared tasks, we have expanded the FLORES+ evaluation set to include Emakhuwa, a low-resource language widely spoken in Mozambique. We translated the dev and devtest sets from Portuguese into Emakhuwa, and we detail the translation process and quality assurance measures used. Our methodology involved various quality checks, including post-editing and adequacy assessments. The resulting datasets consist of multiple reference sentences for each source. We present baseline results from training a Neural Machine Translation system and fine-tuning existing multilingual translation models. Our findings suggest that spelling inconsistencies remain a challenge in Emakhuwa. Additionally, the baseline models underperformed on this evaluation set, underscoring the necessity for further research to enhance machine translation quality for Emakhuwa.The data is publicly available at https://huggingface.co/datasets/LIACC/Emakhuwa-FLORES

Anonymization of clinical text is crucial to allow the sharing and disclosure of health records while safeguarding patient privacy. However, automated anonymization processes are still highly limited in healthcare practice, as these systems cannot assure the anonymization of all private information. This paper explores the application of a novel technique that guarantees the removal of all sensitive information through the usage of text embeddings obtained from a de-identified dataset, replacing every word or sentence of a clinical note. We analyze the performance of different embedding techniques and models by evaluating them using recently proposed evaluation metrics. The results demonstrate that sentence replacement is better at keeping relevant medical information untouched, while the word replacement strategy performs better in terms of anonymization sensitivity.

The accurate identification of loanwords within a given text holds significant potential as a valuable tool for addressing data augmentation and mitigating data sparsity issues. Such identification can improve the performance of various natural language processing tasks, particularly in the context of low-resource languages that lack standardized spelling conventions.This research proposes a supervised method to identify loanwords in Emakhuwa, borrowed from Portuguese. Our methodology encompasses a two-fold approach. Firstly, we employ traditional machine learning algorithms incorporating handcrafted features, including language-specific and similarity-based features. We build upon prior studies to extract similarity features and propose utilizing two external resources: a Sequence-to-Sequence model and a dictionary. This innovative approach allows us to identify loanwords solely by analyzing the target word without prior knowledge about its donor counterpart. Furthermore, we fine-tune the pre-trained CANINE model for the downstream task of loanword detection, which culminates in the impressive achievement of the F1-score of 93%. To the best of our knowledge, this study is the first of its kind focusing on Emakhuwa, and the preliminary results are promising as they pave the way to further advancements.

Interest in argument mining has resulted in an increasing number of argument annotated corpora. However, most focus on English texts with explicit argumentative discourse markers, such as persuasive essays or legal documents. Conversely, we report on the first extensive and consolidated Portuguese argument annotation project focused on opinion articles. We briefly describe the annotation guidelines based on a multi-layered process and analyze the manual annotations produced, highlighting the main challenges of this textual genre. We then conduct a comprehensive inter-annotator agreement analysis, including argumentative discourse units, their classes and relations, and resulting graphs. This analysis reveals that each of these aspects tackles very different kinds of challenges. We observe differences in annotator profiles, motivating our aim of producing a non-aggregated corpus containing the insights of every annotator. We note that the interpretation and identification of token-level arguments is challenging; nevertheless, tasks that focus on higher-level components of the argument structure can obtain considerable agreement. We lay down perspectives on corpus usage, exploiting its multi-faceted nature.

This paper describes our submission to the SemEval 2019 Hyperpartisan News Detection task. Our system aims for a linguistics-based document classification from a minimal set of interpretable features, while maintaining good performance. To this goal, we follow a feature-based approach and perform several experiments with different machine learning classifiers. Additionally, we explore feature importances and distributions among the two classes. On the main task, our model achieved an accuracy of 71.7%, which was improved after the task’s end to 72.9%. We also participate on the meta-learning sub-task, for classifying documents with the binary classifications of all submitted systems as input, achieving an accuracy of 89.9%.

Bias is ubiquitous in most online sources of natural language, from news media to social networks. Given the steady shift in news consumption behavior from traditional outlets to online sources, the automatic detection of propaganda, in which information is shaped to purposefully foster a predetermined agenda, is an increasingly crucial task. To this goal, we explore the task of sentence-level propaganda detection, and experiment with both handcrafted features and learned dense semantic representations. We also experiment with random undersampling of the majority class (non-propaganda) to curb the influence of class distribution on the system’s performance, leading to marked improvements on the minority class (propaganda). Our best performing system uses pre-trained ELMo word embeddings, followed by a bidirectional LSTM and an attention layer. We have submitted a 5-model ensemble of our best performing system to the NLP4IF shared task on sentence-level propaganda detection (team LIACC), achieving rank 10 among 25 participants, with 59.5 F1-score.

Governmental institutions are employing artificial intelligence techniques to deal with their specific problems and exploit their huge amounts of both structured and unstructured information. In particular, natural language processing and machine learning techniques are being used to process citizen feedback. In this paper, we report on the use of such techniques for analyzing and classifying complaints, in the context of the Portuguese Economic and Food Safety Authority. Grounded in its operational process, we address three different classification problems: target economic activity, implied infraction severity level, and institutional competence. We show promising results obtained using feature-based approaches and traditional classifiers, with accuracy scores above 70%, and analyze the shortcomings of our current results and avenues for further improvement, taking into account the intended use of our classifiers in helping human officers to cope with thousands of yearly complaints.

To overcome the lack of annotated resources in less-resourced languages, recent approaches have been proposed to perform unsupervised language adaptation. In this paper, we explore three recent proposals: Adversarial Training, Sentence Encoder Alignment and Shared-Private Architecture. We highlight the differences of these approaches in terms of unlabeled data requirements and capability to overcome additional domain shift in the data. A comparative analysis in two different tasks is conducted, namely on Sentiment Classification and Natural Language Inference. We show that adversarial training methods are more suitable when the source and target language datasets contain other variations in content besides the language shift. Otherwise, sentence encoder alignment methods are very effective and can yield scores on the target language that are close to the source language scores.

Argument mining aims to detect and identify argument structures from textual resources. In this paper, we aim to address the task of argumentative relation identification, a subtask of argument mining, for which several approaches have been recently proposed in a monolingual setting. To overcome the lack of annotated resources in less-resourced languages, we present the first attempt to address this subtask in a cross-lingual setting. We compare two standard strategies for cross-language learning, namely: projection and direct-transfer. Experimental results show that by using unsupervised language adaptation the proposed approaches perform at a competitive level when compared with fully-supervised in-language learning settings.