Explore the vast range of titles available.

While social media offer great communication opportunities, they also increase the vulnerability of young people to threatening situations online. Recent studies report that cyberbullying constitutes a growing problem among youngsters. Successful prevention depends on the adequate detection of potentially harmful messages and the information overload on the Web requires intelligent systems to identify potential risks automatically. The focus of this paper is on automatic cyberbullying detection in social media text by modelling posts written by bullies, victims, and bystanders of online bullying. We describe the collection and fine-grained annotation of a cyberbullying corpus for English and Dutch and perform a series of binary classification experiments to determine the feasibility of automatic cyberbullying detection. We make use of linear support vector machines exploiting a rich feature set and investigate which information sources contribute the most for the task. Experiments on a hold-out test set reveal promising results for the detection of cyberbullying-related posts. After optimisation of the hyperparameters, the classifier yields an F1 score of 64% and 61% for English and Dutch respectively, and considerably outperforms baseline systems.

The detection of online cyberbullying has seen an increase in societal importance, popularity in research, and available open data. Nevertheless, while computational power and affordability of resources continue to increase, the access restrictions on high-quality data limit the applicability of state-of-the-art techniques. Consequently, much of the recent research uses small, heterogeneous datasets, without a thorough evaluation of applicability. In this paper, we further illustrate these issues, as we (i) evaluate many publicly available resources for this task and demonstrate difficulties with data collection. These predominantly yield small datasets that fail to capture the required complex social dynamics and impede direct comparison of progress. We (ii) conduct an extensive set of experiments that indicate a general lack of cross-domain generalization of classifiers trained on these sources, and openly provide this framework to replicate and extend our evaluation criteria. Finally, we (iii) present an effective crowdsourcing method: simulating real-life bullying scenarios in a lab setting generates plausible data that can be effectively used to enrich real data. This largely circumvents the restrictions on data that can be collected, and increases classifier performance. We believe these contributions can aid in improving the empirical practices of future research in the field.

The rapid expansion of artificial intelligence (AI) has triggered significant ethical and human rights concerns. While much of the debate focuses on risks such as discrimination, disinformation and algorithmic bias, much less has been written about AI's potential to support human rights practice and scholarship. This article engages with both perspectives, by reflecting on the early development of RedressHub, a tool that integrates AI-assisted information retrieval with a participatory, stakeholder-driven design to map and connect redress initiatives for colonial harm and its legacies across Europe. We discuss the ethical and epistemological implications of fine-tuning large language models (LLMs) to support the documentation of redress efforts for colonial injustice. Contributing to current debates on process-based, value-driven AI deployment in human rights, we argue that a co-creative approach that engages relevant stakeholders from conceptual design to interface development offers a crucial framework for addressing these challenges. Embedding participation at every stage, this approach has the potential to enhance explainability and contribute to mitigating bias, to open crucial conversations on addressing extractivism and to explore how and under what conditions AI tools can be leveraged to serve the needs and priorities of affected communities.

When using computer-aided translation systems in a typical, professional translation workflow, there are several stages at which there is room for improvement. The SCATE (Smart Computer-Aided Translation Environment) project investigated several of these aspects, both from a human-computer interaction point of view, as well as from a purely technological side. This paper describes the SCATE research with respect to improved fuzzy matching, parallel treebanks, the integration of translation memories with machine translation, quality estimation, terminology extraction from comparable texts, the use of speech recognition in the translation process, and human computer interaction and interface design for the professional translation environment. For each of these topics, we describe the experiments we performed and the conclusions drawn, providing an overview of the highlights of the entire SCATE project.

In this paper, we explore the feasibility of irony detection in Dutch social media. To this end, we investigate both transformer models with embedding representations, as well as traditional machine learning classifiers with extensive feature sets. Our feature-based methodology implements a variety of information sources including lexical, semantic, syntactic, sentiment features, as well as two new data-driven features to model common sense. Based on patterns in the syntactic structure of tweets, we aim to model the presence of contrasting sentiments, a phenomenon that is known to be indicative of verbal irony and sarcasm. Feature selection, as well as voting ensemble techniques were implemented to enhance the classification performance. The final systems reach F1-scores up to 0.79, which are promising results for a task as difficult as irony detection. Besides a quantitative analysis, this paper also describes a thorough qualitative analysis of the system output. Although lexical cues appear to be very important to express irony, our analysis also revealed the need for more advanced modeling of common-sense knowledge to detect more subtle examples of irony.

Automatic term extraction is a productive field of research within natural language processing, but it still faces significant obstacles regarding datasets and evaluation, which require manual term annotation. This is an arduous task, made even more difficult by the lack of a clear distinction between terms and general language, which results in low inter-annotator agreement. There is a large need for well-documented, manually validated datasets, especially in the rising field of multilingual term extraction from comparable corpora, which presents a unique new set of challenges. In this paper, a new approach is presented for both monolingual and multilingual term annotation in comparable corpora. The detailed guidelines with different term labels, the domain- and language-independent methodology and the large volumes annotated in three different languages and four different domains make this a rich resource. The resulting datasets are not just suited for evaluation purposes but can also serve as a general source of information about terms and even as training data for supervised methods. Moreover, the gold standard for multilingual term extraction from comparable corpora contains information about term variants and translation equivalents, which allows an in-depth, nuanced evaluation.

Talking about odors and flavors is difficult for most people, yet experts appear to be able to convey critical information about wines in their reviews. This seems to be a contradiction, and wine expert descriptions are frequently received with criticism. Here, we propose a method for probing the language of wine reviews, and thus offer a means to enhance current vocabularies, and as a by-product question the general assumption that wine reviews are gibberish. By means of two different quantitative analyses—support vector machines for classification and Termhood analysis—on a corpus of online wine reviews, we tested whether wine reviews are written in a consistent manner, and thus may be considered informative; and whether reviews feature domain-specific language. First, a classification paradigm was trained on wine reviews from one set of authors for which the color, grape variety, and origin of a wine were known, and subsequently tested on data from a new author. This analysis revealed that, regardless of individual differences in vocabulary preferences, color and grape variety were predicted with high accuracy. Second, using Termhood as a measure of how words are used in wine reviews in a domain-specific manner compared to other genres in English, a list of 146 wine-specific terms was uncovered. These words were compared to existing lists of wine vocabulary that are currently used to train experts. Some overlap was observed, but there were also gaps revealed in the extant lists, suggesting these lists could be improved by our automatic analysis.

Cross-disciplinary communication is often impeded by terminological ambiguity. Hence, cross-disciplinary teams would greatly benefit from using a language technology-based tool that allows for the (at least semi-) automated resolution of ambiguous terms. Although no such tool is readily available, an interesting theoretical outline of one does exist. The main obstacle for the concrete realization of this tool is the current lack of an effective method for the automatic detection of the different meanings of ambiguous terms across different disciplinary jargons. In this paper, we set up a pilot study to experimentally assess whether the word sense induction technique of 'context clustering', as implemented in the software package 'SenseClusters', might be a solution. More specifically, given several sets of sentences coming from a cross-disciplinary corpus containing a specific ambiguous term, we verify whether this technique can classify each sentence in accordance to the meaning of the ambiguous term in that sentence. For the experiments, we first compile a corpus that represents the disciplinary jargons involved in a project on Bone Tissue Engineering. Next, we conduct two series of experiments. The first series focuses on determining appropriate SenseClusters parameter settings using manually selected test data for the ambiguous target terms 'matrix' and 'model'. The second series evaluates the actual performance of SenseClusters using randomly selected test data for an extended set of target terms. We observe that SenseClusters can successfully classify sentences from a cross-disciplinary corpus according to the meaning of the ambiguous term they contain. Hence, we argue that this implementation of context clustering shows potential as a method for the automatic detection of the meanings of ambiguous terms in cross-disciplinary communication.

Although language modeling has been trending upwards steadily, models available for low-resourced languages are limited to large multilingual models such as mBERT and XLM-RoBERTa, which come with significant overheads for deployment vis-à-vis their model size, inference speeds, etc. We attempt to tackle this problem by proposing a novel methodology to apply knowledge distillation techniques to filter language-specific information from a large multilingual model into a small, fast monolingual model that can often outperform the teacher model. We demonstrate the viability of this methodology on two downstream tasks each for six languages. We further dive into the possible modifications to the basic setup for low-resourced languages by exploring ideas to tune the final vocabulary of the distilled models. Lastly, we perform a detailed ablation study to understand the different components of the setup better and find out what works best for the two under-resourced languages, Swahili and Slovene.

To push the state of the art in text mining applications, research in natural language processing has increasingly been investigating automatic irony detection, but manually annotated irony corpora are scarce. We present the construction of a manually annotated irony corpus based on a fine-grained annotation scheme that allows for identification of different types of irony. We conduct a series of binary classification experiments for automatic irony recognition using a support vector machine (SVM) that exploits a varied feature set and compare this method to a deep learning approach that is based on an LSTM network and (pre-trained) word embeddings. Evaluation on a held-out corpus shows that the SVM model outperforms the neural network approach and benefits from combining lexical, semantic and syntactic information sources. A qualitative analysis of the classification output reveals that the classifier performance may be further enhanced by integrating implicit sentiment information and context- and user-based features.