Refine
Year of publication
- 2017 (279) (remove)
Document Type
- Part of a Book (104)
- Article (84)
- Conference Proceeding (39)
- Book (28)
- Part of Periodical (12)
- Other (5)
- Working Paper (3)
- Report (2)
- Bachelor Thesis (1)
- Periodical (1)
Keywords
- Deutsch (119)
- Korpus <Linguistik> (60)
- Gesprochene Sprache (27)
- Grammatik (13)
- Sprache (13)
- Diskursanalyse (12)
- Rezension (12)
- Wörterbuch (12)
- Corpus linguistics (11)
- Interaktion (11)
Publicationstate
- Veröffentlichungsversion (152)
- Zweitveröffentlichung (12)
- Postprint (11)
- Erstveröffentlichung (1)
- Preprint (1)
Reviewstate
We use a convolutional neural network to perform authorship identification on a very homogeneous dataset of scientific publications. In order to investigate the effect of domain biases, we obscure words below a certain frequency threshold, retaining only their POS-tags. This procedure improves test performance due to better generalization on unseen data. Using our method, we are able to predict the authors of scientific publications in the same discipline at levels well above chance.
This paper presents a survey on hate speech detection. Given the steadily growing body of social media content, the amount of online hate speech is also increasing. Due to the massive scale of the web, methods that automatically detect hate speech are required. Our survey describes key areas that have been explored to automatically recognize these types of utterances using natural language processing. We also discuss limits of those approaches.
We propose a new type of subword embedding designed to provide more information about unknown compounds, a major source for OOV words in German. We present an extrinsic evaluation where we use the compound embeddings as input to a neural dependency parser and compare the results to the ones obtained with other types of embeddings. Our evaluation shows that adding compound embeddings yields a significant improvement of 2% LAS over using word embeddings when no POS information is available. When adding POS embeddings to the input, however, the effect levels out. This suggests that it is not the missing information about the semantics of the unknown words that causes problems for parsing German, but the lack of morphological information for unknown words. To augment our evaluation, we also test the new embeddings in a language modelling task that requires both syntactic and semantic information.
Universal Dependency (UD) annotations, despite their usefulness for cross-lingual tasks and semantic applications, are not optimised for statistical parsing. In the paper, we ask what exactly causes the decrease in parsing accuracy when training a parser on UD-style annotations and whether the effect is similarly strong for all languages. We conduct a series of experiments where we systematically modify individual annotation decisions taken in the UD scheme and show that this results in an increased accuracy for most, but not for all languages. We show that the encoding in the UD scheme, in particular the decision to encode content words as heads, causes an increase in dependency length for nearly all treebanks and an increase in arc direction entropy for many languages, and evaluate the effect this has on parsing accuracy.
To improve grammatical function labelling for German, we augment the labelling component of a neural dependency parser with a decision history. We present different ways to encode the history, using different LSTM architectures, and show that our models yield significant improvements, resulting in a LAS for German that is close to the best result from the SPMRL 2014 shared task (without the reranker).
We introduce a method for error detection in automatically annotated text, aimed at supporting the creation of high-quality language resources at affordable cost. Our method combines an unsupervised generative model with human supervision from active learning. We test our approach on in-domain and out-of-domain data in two languages, in AL simulations and in a real world setting. For all settings, the results show that our method is able to detect annotation errors with high precision and high recall.
Tempuswahn
(2017)
Dass es im Deutschen ein am Verb hängendes "Tempussystem" gäbe und dass dieses Zeitinformationen in die Äußerungen einbringe, gehört zum Grammatikkanon unserer Schulen und auch vieler Lehrerbildungsanstalten und Universitäten, im Ausland, soweit es um Deutsch als Fremdsprache geht, verständlicherweise noch konsequenter als im Inland. Wir brauchen Tempus, um die Sachverhalte, über die wir reden, zeitlich festzumachen – dies kann weithin als opinio communis gelten.
Gezweifelt wurde selten. Harald Weinrich hat immerhin 1964 mit seinem Buch "Tempus. Besprochene und erzählte Welt" das ganze vorgebliche Gemeinwissen in Frage gestellt und damit viel Widerspruch, aber auch positive Reaktionen hervorgerufen. Man muss Weinrich nicht in allen Punkten zustimmen (und ich tue es auch nicht), um doch an der alten Tempustradition irrewerden zu können und nach neuen Tempuskonzeptionen zu suchen.
Im Folgenden wird die Frage behandelt, ob die deutschen Tempora primär mit Zeit zu tun haben und ob es überhaupt sinnvoll ist, für das Deutsche ein Tempussystem anzusetzen.
In the NLP literature, adapting a parser to new text with properties different from the training data is commonly referred to as domain adaptation. In practice, however, the differences between texts from different sources often reflect a mixture of domain and genre properties, and it is by no means clear what impact each of those has on statistical parsing. In this paper, we investigate how differences between articles in a newspaper corpus relate to the concepts of genre and domain and how they influence parsing performance of a transition-based dependency parser. We do this by applying various similarity measures for data point selection and testing their adequacy for creating genre-aware parsing models.
Interview mit Ulrich Engel
(2017)