GermaNet is a large lexical-semantic net that relates German nouns, verbs, and adjectives semantically.The word net has been manually constructed over the last 25 years and hence presents a high-quality, valuable resource for German.While GermaNet is maintained in a Postgres database, all its content can be exported as an XML-based serialisation.Recently, this XML representation has been converted into RDF, largely by staying close to GermaNet's principle of arrangement where lexunits that share the same meaning are grouped together into so-called synsets.With each lexical unit and synset now globally addressable via a unique resource identifier, it has become much easier to link together Ger-maNet entries with other lexical and semantic resources.In terms of semantic interoperability, however, the RDF variant of Ger-maNet leaves much to be desired.In this paper, we describe yet another conversion from Ger-maNet's XML representation to RDF.The new conversion makes use of the OntoLex-Lemon ontology, and therefore, presents a decisive step toward a GermaNet representation with a much higher level of semantic interoperability, and which makes it possible to use GermaNet with other wordnets that already support this conceptualisation of lexica.

In this paper, we introduce the SORTS Subject-Object Resolution Test Suite of German minimal sentence pairs for model introspection. 1 The full test suite consists of 18,502 transitive clauses with manual annotations of 8 word order patterns, 5 morphological and syntactic and 11 semantic property classes.The test suite has been constructed such that sentences are minimal pairs with respect to a property class.Each property has been selected with a particular focus on its effect on subject-object resolution, the second-most error-prone task within syntactic parsing of German after prepositional phrase attachment (Fischer et al., 2019).The size and detail of annotations make the test suite a valuable resource for natural language processing applications with syntactic and semantic tasks.We use dependency parsing to demonstrate how the test suite allows insights into the process of subject-object resolution.Based on the test suite annotations, word order and case syncretism can be identified as most important factors that affect subject-object resolution.

In this paper we present the GerCo dataset of adjective-noun collocations for German, such as alter Freund ‘old friend’ and tiefe Liebe ‘deep love’. The annotation has been performed by experts based on the annotation scheme introduced in this paper. The resulting dataset contains 4,732 positive and negative instances of collocations and covers all the 16 semantic classes of adjectives as defined in the German wordnet GermaNet. The dataset can serve as a reliable empirical basis for comparing different theoretical frameworks concerned with collocations or as material for data-driven approaches to the studies of collocations including different machine learning experiments. This paper addresses the latter issue by using the GerCo dataset for evaluating different models on the task of automatic collocation identification. We compare lexical association measures with static and contextualized word embeddings. The experiments show that word embeddings outperform methods based on statistical association measures by a wide margin.

GermaNet (Henrich and Hinrichs, 2010;Hamp and Feldweg, 1997) is a comprehensive wordnet of Standard German spoken in the Federal Republic of Germany.The GermaNet team aims at modelling the basic vocabulary of the language.German is an official language or a minority language in many countries.It is an official language in Austria, Germany and Switzerland, each with its own codified standard variety (Auer, 2014, p. 21), and also in Belgium, Liechtenstein, and Luxemburg.German is recognized as a minority language in thirteen additional countries, including Brasil, Italy, Poland, and Russia.However, the different standard varieties of German are currently not represented in GermaNet.With this project, we make a start on changing this by including one variety, namely Swiss Standard German, into GermaNet.This shall give a more inclusive perspective on the German language.We will argue that Swiss Standard German words, Helvetisms, are best included into the already existing wordnet GermaNet, rather than creating them as a separate wordnet.

Composition models of distributional semantics are used to construct phrase representations from the representations of their words. Composition models are typically situated on two ends of a spectrum. They either have a small number of parameters but compose all phrases in the same way, or they perform word-specific compositions at the cost of a far larger number of parameters. In this paper we propose transformation weighting (TransWeight), a composition model that consistently outperforms existing models on nominal compounds, adjective-noun phrases, and adverb-adjective phrases in English, German, and Dutch. TransWeight drastically reduces the number of parameters needed compared with the best model in the literature by composing similar words in the same way.

Jianqiang Ma, Erhard Hinrichs. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

A comparison and alignment of lexical resources brings about considerable mutual benefits for all resources involved.For all sense distinctions that are completely parallel in two resources, such an alignment provides supporting external evidence for the validity of sense distinction and allows enriching word senses by information contained in the other resource.By contrast, for all non-matching sense distinctions, reason for revisiting and possibly revising the lexical entries in question is provided.The purpose of this paper is to compare the German wordnet GermaNet with the Digital Dictionary of the German Language (DWDS) and to align word senses in the two resources.The paper presents issues that arise in practice when such an alignment is performed and indicates the benefits that both resources will gain.

Verbal word formation processes involving prefixes and particles are highly productive in Germanic languages.The compositional semantics of such prefix and particle verbs requires an in-depth analysis of the interdependence of their constituent parts for adequately representing these types of complex verbs in lexical-semantic networks.The present paper introduces modeling principles that account for such language-specific phenomena in the German wordnet GermaNet (Hamp and Feldweg, 1997;Henrich and Hinrichs, 2010), considering the continuum between full semantic transparency and highly lexicalized meanings as well as the semantic contribution of the prefix or particle to the meaning of the complex verb as a whole.

This paper introduces the EU-FP7 project CLARIN, a joint effort of over 150 institutions in Europe, aimed at the creation of a sustainable language resources and technology infrastructure for the humanities and social sciences research community. The paper briefly introduces the vision behind the project and how it relates to speech research with a focus on the contributions that CLARIN can and will make to research in spoken language processing. Index Terms: speech research, resources, standardization

Chunk parsing has focused on the recognition of partial constituent structures at the level of individual chunks. Little attention has been paid to the question of how such partial analyses can be combined into larger structures for complete utterances. Such larger structures are not only desirable for a deeper syntactic analysis. They also constitute a necessary prerequisite for assigning function-argument structure.The present paper offers a similarity-based algorithm for assigning functional labels such as subject, object, head, complement, etc. to complete syntactic structures on the basis of prechunked input.The evaluation of the algorithm has concentrated on measuring the quality of functional labels. It was performed on a German and an English treebank using two different annotation schemes at the level of function-argument structure. The results of 89.73 % correct functional labels for German and 90.40 % for English validate the general approach.

This paper describes a compositional semantics for temporal expressions as part of the meaning representation language (MRL) of the JANUS system, a natural language understanding and generation system under joint development by BBN Laboratoires and the Information Sciences Institute. The analysis is based on a higher order intensional logic described in detail in Hinrichs, Ayuso and Scha (1987). Temporal expressions of English are translated into this language as quantifiers over times which bind temporal indices on predicates. The semantic evaluation of time-dependent predicates is defined relative to a set of discourse contexts, which, following Reichenbach (1947), include the parameters of speech time and reference time. The resulting context-dependent and multi-indexed interpretation of temporal expressions solves a set of well-known problems that arise when traditional systems of tense logic are applied to natural language semantics. Based on the principle of rule-to-rule translation, the compositional nature of the analysis provides a straightforward and well-defined interface between the parsing component and the semantic interpretation component of JANUS.