Terminological consistency is an essential requirement for industrial translation. High-quality, hand-crafted terminologies contain entries in their nominal forms. Integrating such a terminology into machine translation is not a trivial task. The MT system must be able to disambiguate homographs on the source side and choose the correct wordform on the target side. In this work, we propose a simple but effective method for homograph disambiguation and a method of wordform selection by introducing multi-choice lexical constraints. We also propose a metric to measure the terminological consistency of the translation. Our results have a significant improvement over the current SOTA in terms of terminological consistency without any loss of the BLEU score. All the code used in this work will be published as open-source.

Context-aware historical text normalisation is a severely under-researched area. To fill the gap we propose a context-aware normalisation approach that relies on the state-of-the-art methods in neural machine translation and transfer learning. We propose a multidialect normaliser with a context-aware reranking of the candidates. The reranker relies on a word-level n-gram language model that is applied to the five best normalisation candidates. The results are evaluated on the historical multidialect datasets of German, Spanish, Portuguese and Slovene. We show that incorporating dialectal information into the training leads to an accuracy improvement on all the datasets. The context-aware reranking gives further improvement over the baseline. For three out of six datasets, we reach a significantly higher accuracy than reported in the previous studies. The other three results are comparable with the current state-of-the-art. The code for the reranker is published as open-source.

The study of argumentation and the development of argument mining tools depends on the availability of annotated data, which is challenging to obtain in sufficient quantity and quality. We present a method that breaks down a popular but relatively complex discourse-level argument annotation scheme into a simpler, iterative procedure that can be applied even by untrained annotators. We apply this method in a crowdsourcing setup and report on the reliability of the annotations obtained. The source code for a tool implementing our annotation method, as well as the sample data we obtained (4909 gold-standard annotations across 982 documents), are freely released to the research community. These are intended to serve the needs of qualitative research into argumentation, as well as of data-driven approaches to argument mining.

This paper presents a newly funded international project for machine translation and automated analysis of ancient cuneiform languages where NLP specialists and Assyriologists collaborate to create an information retrieval system for Sumerian. This research is conceived in response to the need to translate large numbers of administrative texts that are only available in transcription, in order to make them accessible to a wider audience. The methodology includes creation of a specialized NLP pipeline and also the use of linguistic linked open data to increase access to the results.

This paper presents a statistical approach to automatic morphosyntactic annotation of Hittite transcripts. Hittite is an extinct Indo-European language using the cuneiform script. There are currently no morphosyntactic annotations available for Hittite, so we explored methods of distant supervision. The annotations were projected from parallel German translations of the Hittite texts. In order to reduce data sparsity, we applied stemming of German and Hittite texts. As there is no off-the-shelf Hittite stemmer, a stemmer for Hittite was developed for this purpose. The resulting annotation projections were used to train a POS tagger, achieving an accuracy of 69% on a test sample. To our knowledge, this is the first attempt of statistical POS tagging of a cuneiform language.

In this paper, we describe experiments on the morphosyntactic annotation of historical language varieties for the example of Middle Low German (MLG), the official language of the German Hanse during the Middle Ages and a dominant language around the Baltic Sea by the time. To our best knowledge, this is the first experiment in automatically producing morphosyntactic annotations for Middle Low German, and accordingly, no part-of-speech (POS) tagset is currently agreed upon. In our experiment, we illustrate how ontology-based specifications of projected annotations can be employed to circumvent this issue: Instead of training and evaluating against a given tagset, we decomponse it into independent features which are predicted independently by a neural network. Using consistency constraints (axioms) from an ontology, then, the predicted feature probabilities are decoded into a sound ontological representation. Using these representations, we can finally bootstrap a POS tagset capturing only morphosyntactic features which could be reliably predicted. In this way, our approach is capable to optimize precision and recall of morphosyntactic annotations simultaneously with bootstrapping a tagset rather than performing iterative cycles.

We present a new large dataset of 12403 context-sensitive verb relations manually annotated via crowdsourcing. These relations capture fine-grained semantic information between verb-centric propositions, such as temporal or entailment relations. We propose a novel semantic verb relation scheme and design a multi-step annotation approach for scaling-up the annotations using crowdsourcing. We employ several quality measures and report on agreement scores. The resulting dataset is available under a permissive CreativeCommons license at www.ukp.tu-darmstadt.de/data/verb-relations/. It represents a valuable resource for various applications, such as automatic information consolidation or automatic summarization.