Papers by Nils Reiter

5 papers
QUD-Based Annotation of Discourse Structure and Information Structure: Tool and Evaluation (L18-1)

Copied to clipboard

Challenge: a new annotation scheme and discourse-analytic method is developed for information structure annotation.
Approach: They propose a new annotation scheme and a discourse-analytic method based on Questions under Discussion . they introduce a tool which enables the analyst to semi-automatically segment texts and enhance them with QUDs .
Outcome: The proposed method achieves good inter-annotator scores and good agreement with discourse annotations.
Exploring Text Recombination for Automatic Narrative Level Detection (2022.lrec-1)

Copied to clipboard

Challenge: Existing annotation workflows do not scale well to the annotation of complex narrative phenomena.
Approach: They propose a workflow for narrative level detection that includes operationalization and a model . they propose generating training data synthetically to improve the prediction results .
Outcome: The proposed workflow improves predictions by using training data synthetically.
GerDraCor-Coref: A Coreference Corpus for Dramatic Texts in German (2020.lrec-1)

Copied to clipboard

Challenge: Dramatic texts are highly structured literary text types with linguistic and literary properties.
Approach: They present an annotated corpus of German dramatic texts and preliminary experiments on automatic coreference resolution.
Outcome: The proposed system achieves a 28.8 CoNLL score in dramatic texts compared to other dialogical text types such as interviews . the proposed system is expected to be extended to include the (partial) information given in the dramatis personae .
Linguistically-Informed Evaluation of LLMs on Acceptability Judgments in a Forced-Choice Paradigm (2026.acl-srw)

Copied to clipboard

Challenge: Recent studies have reported close alignment with human judgments and systematic divergences driven by response biases and inconsistencies.
Approach: They evaluate large language models' ability to perform acceptability judgments in a forced-choice paradigm.
Outcome: The proposed models approximate human judgments but lack performance on morphosyntactic phenomena and prompt formulations.
Detecting Scenes in Fiction: A new Segmentation Task (2021.eacl-main)

Copied to clipboard

Challenge: Text segmentation is a long standing issue in the area of natural language processing . even modern methods struggle with processing text longer than a couple of sentences or paragraphs .
Approach: They introduce the task of scene segmentation on narrative texts and provide an annotated corpus . they discuss linguistic and narrative properties of the task and provide baseline experiments .
Outcome: The proposed task is very challenging and the results are impressive.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations