Papers by Detmar Meurers
Towards automatically generating Questions under Discussion to link information and discourse structure (2020.coling-main)
Copied to clipboard
| Challenge: | Questions under Discussion (QUD) are emerging as a useful approach to spelling out the connection between information structure of sentences and nature of discourse. |
| Approach: | They propose a framework for QUD annotation based on explicit pragmatic principles . they propose generating all potentially relevant questions for a given sentence . |
| Outcome: | The proposed framework supports more reliable discourse structure annotation based on explicit questions . but the proposed approach is not robust enough for authentic data . |
Automatic Focus Annotation: Bringing Formal Pragmatics Alive in Analyzing the Information Structure of Authentic Data (N18-1)
Copied to clipboard
| Challenge: | Using focus-background dichotomy, discourse and information structure of sentences are being studied in context. |
| Approach: | They propose to automate the analysis of focus in authentic written data by using a range of lexical, syntactic, and semantic features to achieve an accuracy of 78.1%. |
| Outcome: | The proposed approach achieves 78.1% accuracy for identifying focus in authentic written data. |
Grammar Control in Dialogue Response Generation for Language Learning Chatbots (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing language learning chatbots and research on second language acquisition benefit from these affordances. |
| Approach: | They ground a dialogue response generation model in a pedagogical repository of grammar skills and evaluate prompting, fine-tuning, and decoding strategies for grammar-controlled dialogue response generators. |
| Outcome: | The proposed model outperforms GPT-3.5 when tolerating minor response quality losses and predicts grammar-controlled responses to support grammar acquisition adapted to learner proficiency. |
Modeling the Readability of German Targeting Adults and Children: An empirically broad analysis and its cross-corpus validation (C18-1)
Copied to clipboard
| Challenge: | a new corpus of german news broadcast subtitles is compiled and crawled . readability assessment is a task of linking a text to the appropriate target audience based on its complexity. |
| Approach: | They analyze two German educational media texts targeting adults and children . they use 400 automatically extracted measures of linguistic complexity from a wide range of linguistic domains . their most successful binary classification model for german readability shows high accuracy . |
| Outcome: | The proposed model shows high accuracy between 89.4%–98.9% for both data sets. |