Machine Translation (MT) has become an integral part of daily life for millions of people, with its output being so fluent that users often cannot distinguish it from human translation. However, these fluid texts often harbor algorithmic traces, from limited lexical choices to societal misrepresentations. This raises concerns about the possible effects of MT on natural language and human communication and calls for regular evaluations of machine-generated translations for different languages. Our paper explores the output of three widely used engines (Google, DeepL, Microsoft Azure) and one smaller commercial system. We translate the English and French source texts of seven diverse parallel corpora into German and compare MT-produced texts to human references in terms of lexical, syntactic, and morphological features. Additionally, we investigate how MT leverages lexical borrowings and analyse the distribution of anglicisms across the German translations.
In 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 data.
In 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 a BERT-based intensity regressor. We evaluated the quality of the silver standard empirically and found that our lexicon-based quantification metric showed a strong correlation with human annotators.
In this paper, we introduce the first corpus specifying negative entities within sentences. We discuss indicators for their presence, namely particular verbs, but also the linguistic conditions when their prediction should be suppressed. We further show that a fine-tuned Bert-based baseline model outperforms an over-generating rule-based approach which is not aware of these further restrictions. If a perfect filter were applied, both would be on par.
Text normalization is the task of mapping non-canonical language, typical of speech transcription and computer-mediated communication, to a standardized writing. It is an up-stream task necessary to enable the subsequent direct employment of standard natural language processing tools and indispensable for languages such as Swiss German, with strong regional variation and no written standard. Text normalization has been addressed with a variety of methods, most successfully with character-level statistical machine translation (CSMT). In the meantime, machine translation has changed and the new methods, known as neural encoder-decoder (ED) models, resulted in remarkable improvements. Text normalization, however, has not yet followed. A number of neural methods have been tried, but CSMT remains the state-of-the-art. In this work, we normalize Swiss German WhatsApp messages using the ED framework. We exploit the flexibility of this framework, which allows us to learn from the same training data in different ways. In particular, we modify the decoding stage of a plain ED model to include target-side language models operating at different levels of granularity: characters and words. Our systematic comparison shows that our approach results in an improvement over the CSMT state-of-the-art.
This paper describes the process of constructing a trilingual parallel treebank. While for two of the involved languages, Spanish and German, there are already corpora with well-established annotation schemes available, this is not the case with the third language: Cuzco Quechua (ISO 639-3:quz), a low-resourced, non-standardized language for which we had to define a linguistically plausible annotation scheme first.
Cet article présente un corpus parallèle français-allemand de plus de 4 millions de mots issu de la numérisation d’un corpus alpin multilingue. Ce corpus est une précieuse ressource pour de nombreuses études de linguistique comparée et du patrimoine culturel ainsi que pour le développement d’un système statistique de traduction automatique dans un domaine spécifique. Nous avons annoté un échantillon de ce corpus parallèle et aligné les structures arborées au niveau des mots, des constituants et des phrases. Cet “alpine treebank” est le premier corpus arboré parallèle français-allemand de haute qualité (manuellement contrôlé), de libre accès et dans un domaine et un genre nouveau : le récit d’alpinisme.