No abstract

Various semantic relatedness, similarity, and distance measures have been proposed in the past decade and many NLP-applications strongly rely on these semantic measures. Researchers compete for better algorithms and normally only few percentage points seem to suffice in order to prove a new measure outperforms an older one. In this paper we present a metastudy comparing various semantic measures and their correlation with human judgments. We show that the results are rather inconsistent and ask for detailed analyses as well as clarification. We argue that the definition of a shared task might bring us considerably closer to understanding the concept of semantic relatedness.

Annotating large text corpora is a timeconsuming effort. Although single-user annotation tools are available, web-based annotation applications allow for distributed annotation and file access from different locations. In this paper we present the webbased annotation application Serengeti for annotating anaphoric relations which will be extended for the annotation of lexical chains.

Abstract. Word nets, such as Princeton WordNet or GermaNet, are resources organizing a (more or less extensive) fraction of the vocabulary of a language according to lexical semantic relations. Such resources are widely used in natural language processing (NLP) and computational linguistics (CL) both for research and teaching purposes. While several graphical user interfaces (GUI) exist for Princeton WordNet-some of which are also available online -GermaNet still lacks such utilities. In this paper we describe two GUI-based tools meant to facilitate the navigation through and exploration of GermaNet. Both are freely available for download from our project web page (www.hytex.info). We additionally discuss ways of deploying these tools in teaching. We argue that the GUI-based access to word nets, which can be regarded as a fundamental resource in CL and NLP, enhances the students' understanding of basic lexical semantic concepts, computational semantics and lexicography. MotivationWord nets are lexical semantic resources modeled according to the principles introduced in Princeton WordNet (e.g. Fellbaum 1998

No abstract