Articles

AbstractVisual Question Answering (VQA) is a challenge problem that can advance AI by integrating several important sub-disciplines including natural language understanding and computer vision. Large VQA datasets that are publicly available for training and evaluation have driven the growth of VQA models that have obtained increasingly larger accuracy scores. However, …...

AbstractTransformer-based models showed near-perfect results on several downstream tasks. However, their performance on classical Arabic texts is largely unexplored. To fill this gap, we evaluate monolingual, bilingual, and multilingual state-of-the-art models to detect relatedness between the Quran (Muslim holy book) and the Hadith (Prophet Muhammed teachings), which are complex classical …...

AbstractFrom both human translators (HT) and machine translation (MT) researchers’ point of view, translation quality evaluation (TQE) is an essential task. Translation service providers (TSPs) have to deliver large volumes of translations which meet customer specifications with harsh constraints of required quality level in tight time-frames and costs. MT researchers …...

AbstractTimeML is a scheme for representing temporal information (times, events, & temporal relations) in texts. Although automatic TimeML annotation is challenging, there has been notable progress, with F1s of 0.8–0.9 for events and time detection subtasks, and F1s of 0.5–0.7 for relation extraction. Individually, these subtask results are reasonable, even …...

AbstractA significant challenge in developing translation systems for the world’s ∼7,000 languages is that very few have sufficient data for state-of-the-art techniques. Transfer learning is a promising direction for low-resource neural machine translation (NMT), but introduces many new variables which are often selected through ablation studies, costly trial-and-error, or niche …...

AbstractOne of the processing tasks for large multimodal data streams is automatic image description (image classification, object segmentation and classification). Although the number and the diversity of image datasets is constantly expanding, still there is a huge demand for more datasets in terms of variety of domains and object classes …...

AbstractThis paper addresses the semi-automatic annotation of subjects, also called policy areas, in the Danish Parliament Corpus (2009-2017) v.2. Recently, the corpus has been made available through the CLARIN-DK repository, the Danish node of the European CLARIN infrastructure. The paper also contains an analysis of the subjects in the corpus, …...

AbstractAs input representation for each sub-word, the original BERT architecture proposes the sum of the sub-word embedding, position embedding and a segment embedding. Sub-word and position embeddings are well-known and studied, and encode lexical information and word position, respectively. In contrast, segment embeddings are less known and have so far …...

AbstractMultiple works have proposed to probe language models (LMs) for generalization in named entity (NE) typing (NET) and recognition (NER). However, little has been done in this direction for auto-regressive models despite their popularity and potential to express a wide variety of NLP tasks in the same unified format. We …...

AbstractThe traditional evaluation of labeled spans with precision, recall, and F1-score has undesirable effects due to double penalties. Annotations with incorrect label or boundaries count as two errors instead of one, despite being closer to the target annotation than false positives or false negatives. In this paper, new error types …...

AbstractIn this paper, we introduce a new Czech subjectivity dataset of 10k manually annotated subjective and objective sentences from movie reviews and descriptions. Our prime motivation is to provide a reliable dataset that can be used with the existing English dataset as a benchmark to test the ability of pre-trained …...

AbstractRED (Romanian Emotion Dataset) is a machine learning-based resource developed for the automatic detection of emotions in Romanian texts, containing single-label annotated tweets with one of the following emotions: joy, fear, sadness, anger and neutral. In this work, we propose REDv2, an open-source extension of RED by adding two more …...

AbstractIn this paper, we discuss work that strives to measure the degree of negativity - the negative polar load - of noun phrases, especially those denoting actors. Since no gold standard data is available for German for this quantification task, we generated a silver standard and used it to fine-tune …...

AbstractEmotion classification is often formulated as the task to categorize texts into a predefined set of emotion classes. So far, this task has been the recognition of the emotion of writers and readers, as well as that of entities mentioned in the text. We argue that a classification setup for …...

AbstractIn this paper, we introduce a gold standard for animacy detection comprising almost 14,500 German nouns that might be used to denote either animate entities or non-animate entities. We present inter-annotator agreement of our crowd-sourced seed annotations (9,000 nouns) and discuss the results of machine learning models applied to this …...

AbstractTerminology databases are highly useful for the dissemination of specialized knowledge. In this paper we present TZOS, an online terminology database to work on Basque academic terminology collaboratively. We show how this resource integrates the Communicative Theory of Terminology, together with the methodological matters, how it is connected with real …...

AbstractWe present NomVallex, a manually annotated valency lexicon of Czech nouns and adjectives. The lexicon is created in the theoretical framework of the Functional Generative Description and based on corpus data. In total, NomVallex 2.0 is comprised of 1027 lexical units contained in 570 lexemes, covering the following part-of-speech and …...

AbstractWe present an extension of the SynSemClass Event-type Ontology, originally conceived as a bilingual Czech-English resource. We added German entries to the classes representing the concepts of the ontology. Having a different starting point than the original work (unannotated parallel corpus without links to a valency lexicon and, of course, …...

AbstractWhat makes a text easy to read or not, depends on a variety of factors. One of the most prominent is, however, if the text contains easy, and avoids difficult, words. Deciding if a word is easy or difficult is not a trivial task, since it depends on characteristics of …...

AbstractWe present a machine-readable structured data version of Wiktionary. Unlike previous Wiktionary extractions, the new extractor, Wiktextract, fully interprets and expands templates and Lua modules in Wiktionary. This enables it to perform a more complete, robust, and maintainable extraction. The extracted data is multilingual and includes lemmas, inflected forms, translations, …...