AET: Web-based Adjective Exploration Tool for German

AET: Web-based Adjective Exploration Tool for German Tatiana Bladier, Esther Seyffarth, Oliver Hellwig, Wiebke Petersen Heinrich Heine University of D¨usseldorf, Germany bladier@phil.hhu.de, seyffarth@phil.hhu.de, hellwig7@gmx.de, petersen@phil.hhu.de Abstract We present a new web-based corpus query tool, the Adjective Exploration Tool (AET), which enables research on the modificational behavior of German adjectives and adverbs. The tool can also be transferred to other languages and modification phenomena. The underlying database is derived from a corpus of German print media texts, which we annnotated with dependency parses and several morphological, lexical, and statistical properties of the tokens. We extracted pairs of adjectives and adverbs (modifiers) as well as the tokens modified by them (modifiees) from the corpus and stored them in a way that makes the modifier-modifiee pairs easily searchable. With AET, linguists from different research areas can access corpus samples using an intuitive query language and user-friendly web interface. AET has been developed as a part of a collaborative research project that focuses on the compositional interaction of attributive adjectives with nouns and the interplay of events and adverbial modifiers. The tool is easy to extend and update and is free to use online without registration: http://aet.phil.hhu.de Keywords: Corpus-query tool, adjectives, adjective modification, German, syntactic dependencies 1. Introduction Current research on semantic compositionality, relatedness, clustering and distributional properties of adjectives and adverbials in German (Eroms, 2011; Hartung and Frank, 2011; Dalmas et al., 2015; Petersen and Hellwig, 2016) requires access to corpus tools which enable linguists to answer complex questions about the behavior of the adjec- tives in their context. These questions may, for instance, relate to the syntactic relationships or morphological prop- erties of the adjectives at hand. Currently available online corpus query tools for German include the Stuttgarter IMS WORKBENCH tool (Evert and Hardie, 2011), COSMAS II (Kupietz and Keibel, 2009) and DWDS (Klein and Geyken, 2010). These and other resources provide data that is anno- tated on several linguistic levels, but do not lend themselves specifically to research on adjectives. In particular, we are not aware of any freely accessible corpus query tools that offer the possibility to easily filter the corpora according to complex syntactic or morphological (e. g. derivational) criteria. In this paper, we present a user-friendly, web-based cor- pus query tool designed for linguists researching different aspects of usage patterns of adjectives and adverbs in Ger- man. The underlying corpus of our Adjective Exploration Tool (AET) is based on a subset of the corpora from the Workshop on Machine Translation 2014 (WMT14) shared tasks (Bojar et al., 2014)1 and contains texts from Ger- man print media. In addition to the corpus text itself, the AET database also contains data on syntactic dependen- cies, word co-occurrences, morphological properties of the occurring tokens, and frequency statistics for the adjectives and adverbs. We store dependency-parsed sentences in a relational MySQL database, capturing direct modification2 relations between the modifiers (i.e., adjectives or adverbs) 1The file is available at http://www.statmt.org/wmt14/ training-monolingual-news-crawl/news.2013.de.shuffled.gz. 2In this paper, we use the term modification as an umbrella term …

Content truncated to 500 words