- English (3) (remove)
- Unity in diversity : integrating differing linguistic data in TUSNELDA (2005)
- This paper describes the creation and preparation of TUSNELDA, a collection of corpus data built for linguistic research. This collection contains a number of linguistically annotated corpora which differ in various aspects such as language, text sorts / data types, encoded annotation levels, and linguistic theories underlying the annotation. The paper focuses on this variation on the one hand and the way how these heterogeneous data are integrated into one resource on the other hand.
- The TUSNELDA annotation standard : an XML encoding standard for multilingual corpora supporting various aspects of linguistic research (2000)
- This paper proposes a corpus encoding standard that meets the needs of linguistic research using a variety of linguistic data structures. The standard was developed in SFB 441, a research project at the University of Tuebingen. The principal concern of SFB 441 are the empirical data structures which feed into linguistic theory building. SFB 441 consists of several projects, most of which are building corpora to empirically investigate various linguistic phenomena in various languages (e.g. modal verbs in German, forms of address and politeness in Russian). These corpora will form the components of the "Tuebingen collection of reusable, empirical, linguistic data structures (TUSNELDA)". The TUSNELDA annotation standard aims at providing a uniform encoding scheme for all subcorpora and texts of TUSNELDA such that they can be processed with uniform standardized tools. To guarantee maximal reusability we use XML for encoding. Previous SGML standards for text encoding were provided by the Text Encoding Initiative (TEI) and the Expert Advisory Group on Language Engineering Standards (Corpus Encoding Standard, CES). The TUSNELDA standard is based on TEI and XCES (XML version of CES) but takes into account the specific needs of the SFB projects, i.e. the peculiarities of the examined languages and linguistic phenomena.
- Evaluating POS tagging under sub-optimal conditions : or: does meticulousness pay? (2000)
- In this paper, we investigate the role of sub-optimality in training data for part-of-speech tagging. In particular, we examine to what extent the size of the training corpus and certain types of errors in it affect the performance of the tagger. We distinguish four types of errors: If a word is assigned a wrong tag, this tag can belong to the ambiguity class of the word (i.e. to the set of possible tags for that word) or not; furthermore, the major syntactic category (e.g. "N" or "V") can be correctly assigned (e.g. if a finite verb is classified as an infinitive) or not (e.g. if a verb is classified as a noun). We empirically explore the decrease of performance that each of these error types causes for different sizes of the training set. Our results show that those types of errors that are easier to eliminate have a particularly negative effect on the performance. Thus, it is worthwhile concentrating on the elimination of these types of errors, especially if the training corpus is large.