Eva Belke


2024

pdf
Automatic Extraction of Nominal Phrases from German Learner Texts of Different Proficiency Levels
Ronja Laarmann-Quante | Marco Müller | Eva Belke
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Correctly inflecting determiners and adjectives so that they agree with the noun in nominal phrases (NPs) is a big challenge for learners of German. Given the increasing number of available learner corpora, a large-scale corpus-based study on the acquisition of this aspect of German morphosyntax would be desirable. In this paper, we present a pilot study in which we investigate how well nouns, their grammatical heads and the dependents that have to agree with the noun can be extracted automatically via dependency parsing. For six samples of the German learner corpus MERLIN (one per proficiency level), we found that in spite of many ungrammatical sentences in texts of low proficiency levels, human annotators find only few true ambiguities that would make the extraction of NPs and their heads infeasible. The automatic parsers, however, perform rather poorly on extracting the relevant elements for texts on CEFR levels A1-B1 (< 70%) but quite well from level B2 onwards ( 90%). We discuss the sources of errors and how performance could potentially be increased in the future.

2019

pdf
The making of the Litkey Corpus, a richly annotated longitudinal corpus of German texts written by primary school children
Ronja Laarmann-Quante | Stefanie Dipper | Eva Belke
Proceedings of the 13th Linguistic Annotation Workshop

To date, corpus and computational linguistic work on written language acquisition has mostly dealt with second language learners who have usually already mastered orthography acquisition in their first language. In this paper, we present the Litkey Corpus, a richly-annotated longitudinal corpus of written texts produced by primary school children in Germany from grades 2 to 4. The paper focuses on the (semi-)automatic annotation procedure at various linguistic levels, which include POS tags, features of the word-internal structure (phonemes, syllables, morphemes) and key orthographic features of the target words as well as a categorization of spelling errors. Comprehensive evaluations show that high accuracy was achieved on all levels, making the Litkey Corpus a useful resource for corpus-based research on literacy acquisition of German primary school children and for developing NLP tools for educational purposes. The corpus is freely available under https://www.linguistics.rub.de/litkeycorpus/.