Refine
Year of publication
- 2013 (286) (remove)
Document Type
- Part of a Book (132)
- Article (88)
- Conference Proceeding (27)
- Book (18)
- Part of Periodical (10)
- Review (4)
- Doctoral Thesis (3)
- Other (1)
- Preprint (1)
- Report (1)
Has Fulltext
- yes (286) (remove)
Keywords
- Deutsch (135)
- Korpus <Linguistik> (22)
- Mediensprache (17)
- Lexikographie (15)
- Massenmedien (14)
- Konversationsanalyse (13)
- Wörterbuch (13)
- Englisch (12)
- Gesprochene Sprache (11)
- Syntax (11)
Publicationstate
- Veröffentlichungsversion (87)
- Zweitveröffentlichung (27)
- Postprint (14)
- (Verlags)-Lektorat (1)
Reviewstate
- (Verlags)-Lektorat (71)
- Peer-Review (38)
- Verlags-Lektorat (12)
- Qualifikationsarbeit (Dissertation, Habilitationsschrift) (2)
- Peer review (1)
- Peer-review (1)
- Review-Status-unbekannt (1)
- Zweitveröffentlichung (1)
Publisher
- Institut für Deutsche Sprache (40)
- de Gruyter (33)
- De Gruyter (19)
- Narr (15)
- Lang (8)
- Benjamins (6)
- Elsevier (5)
- Springer (5)
- Olms (4)
- Verlag der Universität Wolgograd (4)
We examine predicative adjectives as an unsupervised criterion to extract subjective adjectives. We do not only compare this criterion with a weakly supervised extraction method but also with gradable adjectives, i.e. another highly subjective subset of adjectives that can be extracted in an unsupervised fashion. In order to prove the robustness of this extraction method, we will evaluate the extraction with the help of two different state-of-the-art sentiment lexicons (as a gold standard).
In this article, we examine the effectiveness of bootstrapping supervised machine-learning polarity classifiers with the help of a domain-independent rule-based classifier that relies on a lexical resource, i.e., a polarity lexicon and a set of linguistic rules. The benefit of this method is that though no labeled training data are required, it allows a classifier to capture in-domain knowledge by training a supervised classifier with in-domain features, such as bag of words, on instances labeled by a rule-based classifier. Thus, this approach can be considered as a simple and effective method for domain adaptation. Among the list of components of this approach, we investigate how important the quality of the rule-based classifier is and what features are useful for the supervised classifier. In particular, the former addresses the issue in how far linguistic modeling is relevant for this task. We not only examine how this method performs under more difficult settings in which classes are not balanced and mixed reviews are included in the data set but also compare how this linguistically-driven method relates to state-of-the-art statistical domain adaptation.
We explore the feasibility of contextual healthiness classification of food items. We present a detailed analysis of the linguistic phenomena that need to be taken into consideration for this task based on a specially annotated corpus extracted from web forum entries. For automatic classification, we compare a supervised classifier and rule-based classification. Beyond linguistically motivated features that include sentiment information we also consider the prior healthiness of food items.
We investigate the task of detecting reliable statements about food-health relationships from natural language texts. For that purpose, we created a specially annotated web corpus from forum entries discussing the healthiness of certain food items. We examine a set of task-specific features (mostly) based on linguistic insights that are instrumental in finding utterances that are commonly perceived as reliable. These features are incorporated in a supervised classifier and compared against standard features that are widely used for various tasks in natural language processing, such as bag of words, part-of speech and syntactic parse information.
Opinion holder extraction is one of the most important tasks in sentiment analysis. We will briefly outline the importance of predicates for this task and categorize them according to part of speech and according to which semantic role they select for the opinion holder. For many languages there do not exist semantic resources from which such predicates can be easily extracted. Therefore, we present alternative corpus-based methods to gain such predicates automatically, including the usage of prototypical opinion holders, i.e. common nouns, denoting for example experts or analysts, which describe particular groups of people whose profession or occupation is to form and express opinions towards specific items.
Sexual harassment severely impacts the educational system in the West African country Benin and the progress of women in this society that is characterized by great gender inequality. Knowledge of the belief systems rooting in the sociocultural context is crucial to the understanding of sexual harassment. However, no study has yet investigated how sexual harassment is related to fundamental beliefs in Benin or West African countries. We conducted a field study on 265 female and male students from several high schools in Benin to investigate the link between sexual harassment and measures of ambivalent sexism, gender identity, and rape myth acceptance. Almost half of the sample reported having experienced sexual harassment personally or among peers. Levels of sexism and rape myth acceptance were very high compared to other studies. These attitudes appeared to converge in a sexist belief system that was linked to personal experiences, the perceived probability of experiencing and fear of sexual harassment. Results suggest that sexual harassment is a societal problem and that interventions need to address fundamental attitudes held in societies low in gender equality.
Die Wortbildungsangaben im Online-Wörterbuch und wie Nutzer sie beurteilen – eine Umfrage zu elexiko
(2013)
Der vorliegende Beitrag betrachtet das Thema der Wortbildung im Online-Wörterbuch aus der Perspektive der Wörterbuchbenutzer. Zunächst werden an einzelnen Beispielen die unterschiedlichen Angabebereiche im Internetwörterbuch und die verschiedenen Arten der Wortbildungsangaben aufgezeigt, auf die ein Wörterbuchbenutzer beim Nachschlagen stoßen kann (Kap. 2). Daran anschließend werden mit elexiko und BZVelexiko kurz die beiden Projekte vorgestellt, die an den Mannheimer Nutzerumfragen beteiligt waren. Schließlich werden die Ergebnisse zweier Online-Befragungen präsentiert, die Anfang 2011 am Institut für Deutsche Sprache durchgeführt wurden und an denen insgesamt über 1 100 Personen teilnahmen. In diesem Kontext stehen dabei allein die Teilergebnisse zum Thema Wortbildung im Mittelpunkt (Kap. 3). Ein Ausblick auf die weitere geplante Forschung rundet den Beitrag ab (Kap. 4).