Computerlinguistik
Refine
Year of publication
Document Type
- Part of a Book (12)
- Conference Proceeding (5)
- Article (1)
- Book (1)
Has Fulltext
- yes (19)
Keywords
- Automatische Sprachverarbeitung (19) (remove)
Publicationstate
Reviewstate
- Peer-Review (13)
- (Verlags)-Lektorat (5)
- Review-Status-unbekannt (1)
Publisher
- The Association for Computational Linguistics (5)
- Austrian Academy of Sciences (2)
- de Gruyter (2)
- Deutsche Gesellschaft für Sprachwissenschaft (1)
- GSCL (1)
- Heidelberg University Publishing (1)
- Incoma Ltd. (1)
- Linköping University Electronic Press, Linköpings universitet (1)
- Press Universitaires Savoie Mont Blanc (1)
- VS Verlag für Sozialwissenschaften (1)
In our paper, we present a case study on the quality of concept relations in the manually developed terminological resource of grammis, an information system on German grammar. We assess a SKOS representation of the resource using the tool qSKOS, create a typology of the issues identified by the tool, and conduct a qualitative analysis of selected cases. We identify and discuss aspects that can motivate quality issues and uncover that ill-formed relations are frequently indicative of deeper issues in the data model. Finally, we outline how these findings can inform improvements in our resource’s data model, discussing implications for the machine readability of terminological data.
We propose a Cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with Semantic Role Labeling annotations in a resource-poor target language. Unlike annotation projection techniques, our model does not need parallel data during inference time. Our approach can be applied in monolingual, multilingual and cross-lingual settings and is able to produce dependencybased and span-based SRL annotations. We benchmark the labeling performance of our model in different monolingual and multilingual settings using well-known SRL datasets. We then train our model in a cross-lingual setting to generate new SRL labeled data. Finally, we measure the effectiveness of our method by using the generated data to augment the training basis for resource-poor languages and perform manual evaluation to show that it produces high-quality sentences and assigns accurate semantic role annotations. Our proposed architecture offers a flexible method for leveraging SRL data in multiple languages.
We present an approach for automatic detection and correction of OCR-induced misspellings in historical texts. The main objective is the post-correction of the digitized Royal Society Corpus, a set of historical documents from 1665 to 1869. Due to the aged material the OCR procedure has made mistakes, thus leading to files corrupted by thousands of misspellings. This motivates a post processing step. The current correction technique is a pattern-based approach which due to its lack of generalization suffers from bad recall.
To generalize from the patterns we propose to use the noisy channel model. From the pattern based substitutions we train a corpus specific error model complemented with a language model. With an F1-Score of 0.61 the presented technique significantly outperforms the pattern based approach which has an F1-score of 0.28. Due to its more accurate error model it also outperforms other implementations of the noisy channel model.
Unknown words are a challenge for any NLP task, including sentiment analysis. Here, we evaluate the extent to which sentiment polarity of complex words can be predicted based on their morphological make-up. We do this on German as it has very productive processes of derivation and compounding and many German hapax words, which are likely to bear sentiment, are morphologically complex. We present results of supervised classification experiments on new datasets with morphological parses and polarity annotations.
We study German affixoids, a type of morpheme in between affixes and free stems. Several properties have been associated with them – increased productivity; a bleached semantics, which is often evaluative and/or intensifying and thus of relevance to sentiment analysis; and the existence of a free morpheme counterpart – but not been validated empirically. In experiments on a new data set that we make available, we put these key assumptions from the morphological literature to the test and show that despite the fact that affixoids generate many low-frequency formations, we can classify these as affixoid or non-affixoid instances with a best F1-score of 74%.
In this paper we use methods for creating a large lexicon of verbal polarity shifters and apply them to German. Polarity shifters are content words that can move the polarity of a phrase towards its opposite, such as the verb “abandon” in “abandon all hope”. This is similar to how negation words like “not” can influence polarity. Both shifters and negation are required for high precision sentiment analysis. Lists of negation words are available for many languages, but the only language for which a sizable lexicon of verbal polarity shifters exists is English. This lexicon was created by bootstrapping a sample of annotated verbs with a supervised classifier that uses a set of data- and resource-driven features. We reproduce and adapt this approach to create a German lexicon of verbal polarity shifters. Thereby, we confirm that the approach works for multiple languages. We further improve classification by leveraging cross-lingual information from the English shifter lexicon. Using this improved approach, we bootstrap a large number of German verbal polarity shifters, reducing the annotation effort drastically. The resulting German lexicon of verbal polarity shifters is made publicly available.
Both for psychology and linguistics, emotion concepts are a continuing challenge for analysis in several respects. In this contribution, we take up the language of emotion as an object of study from several angles. First, we consider how frame semantic analyses of this domain by the FrameNet project have been developing over time, due to theory-internal as well as application-oriented goals, towards ever more fine-grained distinctions and greater within-frame consistency. Second, we compare how FrameNet’s linguistically oriented analysis of lexical items in the emotion domain compares to the analysis by domain experts of the experiences that give rise (directly or indirectly) to the lexical items. And finally, we consider to what extent frame semantic analysis can capture phenomena such as connotation and inference about attitudes, which are important in the field of sentiment analysis and opinion mining, even if they do not involve the direct evocation of emotion.
We present the pilot edition of the GermEval Shared Task on the Identification of Offensive Language. This shared task deals with the classification of German tweets from Twitter. It comprises two tasks, a coarse-grained binary classification task and a fine-grained multi-class classification task. The shared task had 20 participants submitting 51 runs for the coarse-grained task and 25 runs for the fine-grained task. Since this is a pilot task, we describe the process of extracting the raw-data for the data collection and the annotation schema. We evaluate the results of the systems submitted to the shared task. The shared task homepage can be found at https://projects.cai. fbi.h-da.de/iggsa/
Offensive language in social media is a problem currently widely discussed. Researchers in language technology have started to work on solutions to support the classification of offensive posts. We present the pilot edition of the GermEval Shared Task on the Identification of Offensive Language. This shared task deals with the classification of German tweets from Twitter. GermEval 2018 is the fourth workshop in a series of shared tasks on German processing.