Papers with large scale analysis
Using a Knowledge Base to Automatically Annotate Speech Corpora and to Identify Sociolinguistic Variation (2022.lrec-1)
Copied to clipboard
| Challenge: | Speech characteristics vary from speaker to speaker due to many factors, including communication context, provenance, age, and social background. |
| Approach: | They propose a method that uses a knowledge base to provide speaker-specific information. |
| Outcome: | The proposed method can be used to enrich existing corpora with speaker-specific information and to correlate with diastratic features. |
PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry (2020.lrec-1)
Copied to clipboard
| Challenge: | a new study shows that literature enables engagement in a broader range of complex and subtle emotions. |
| Approach: | They propose to use multiple emotion labels to capture mixed emotions in poetry . they evaluate an annotation experiment with experts and crowdsourcing . |
| Outcome: | The proposed method shows that identifying aesthetic emotions is challenging in the German subset. |
Metrical Tagging in the Wild: Building and Annotating Poetry Corpora with Rhythmic Features (2021.eacl-main)
Copied to clipboard
| Challenge: | a prerequisite for the computational study of literature is the availability of properly digitized texts with reliable meta-data and ground-truth annotation. |
| Approach: | They propose to annotate prosodic features in large poetry corpora for English and German and train corpus driven neural models that enable large scale analysis. |
| Outcome: | The proposed models outperform baseline and BERT-based approaches in English and german and show that they learn foot boundaries better when jointly predicting syllable stress, aesthetic emotions and verse measures benefit from each other. |
Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild (2025.emnlp-main)
Copied to clipboard
| Challenge: | Rather than passively accepting output, users actively refine, explore, and co-construct text. |
| Approach: | They conduct a large scale analysis of user-LLM collaboration behavior with two popular AI assistants, Bing Copilot and WildChat. |
| Outcome: | The proposed models show that a small group of prototypical human AI collaboration behaviors explain a majority of the variation seen in user-LLM interaction. |