Papers with German news

5 papers
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.
Adversarial Training for Satire Detection: Controlling for Confounding Variables (N19-1)

Copied to clipboard

Challenge: Existing methods for satire detection focus on satirical news based on article sources . satiric news are written with the aim of mimicking regular news in diction .
Approach: They propose a model for satire detection with an adversarial component to control for the confounding variable of publication source.
Outcome: The proposed model improves generalization performance to unseen publications with an adversarial component.
Uncovering Temporal Framing in the News (2026.acl-long)

Copied to clipboard

Challenge: Temporal language is used to structure meaning rather than report chronology in news discourse . a recent study focused on temporal expression extraction and temporal reasoning .
Approach: They propose a taxonomy of eight temporal frames grounded in prior work on time and framing . they analyze frame prevalence, co-occurrence patterns, and lexical cues from a news corpus .
Outcome: The proposed taxonomy outperforms zero-shot models at the sentence level . it shows that temporal framing is learnable at the sentences level compared to other methods .
Dataset of Quotation Attribution in German News Articles (2024.lrec-main)

Copied to clipboard

Challenge: Lack of annotated data for quotation attribution in news articles severely limits the quality and usability of possible systems.
Approach: They propose a dataset for quotation attribution in German news articles using WIKINEWS and manually annotated quotes from 1000 articles.
Outcome: The proposed dataset provides curated, high-quality annotations across 1000 documents (250,000 tokens) in a fine-grained annotation schema enabling various downstream uses for the dataset.
German Also Hallucinates! Inconsistency Detection in News Summaries with the Absinth Dataset (2024.lrec-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have made significant progress on a wide range of natural language processing tasks, but they still suffer from hallucinating information in their output.
Approach: They propose to use an annotated dataset to detect hallucinations in german news summarization and open-source it to foster further research on hallucinosity detection in german.
Outcome: The proposed model can detect hallucinations in the output and evaluate the faithfulness of the summaries.

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