Annotate Rhetorical Relations with INCEpTION: A Comparison with Automatic Approaches
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914075343060992 |
|---|---|
| author | Emon, Mehedi Hasan |
| author_facet | Emon, Mehedi Hasan |
| contents | This research explores the annotation of rhetorical relations in discourse using the INCEpTION tool and compares manual annotation with automatic approaches based on large language models. The study focuses on sports reports (specifically cricket news) and evaluates the performance of BERT, DistilBERT, and Logistic Regression models in classifying rhetorical relations such as elaboration, contrast, background, and cause-effect. The results show that DistilBERT achieved the highest accuracy, highlighting its potential for efficient discourse relation prediction. This work contributes to the growing intersection of discourse parsing and transformer-based NLP. (This paper was conducted as part of an academic requirement under the supervision of Prof. Dr. Ralf Klabunde, Linguistic Data Science Lab, Ruhr University Bochum.) Keywords: Rhetorical Structure Theory, INCEpTION, BERT, DistilBERT, Discourse Parsing, NLP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03808 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Annotate Rhetorical Relations with INCEpTION: A Comparison with Automatic Approaches Emon, Mehedi Hasan Computation and Language This research explores the annotation of rhetorical relations in discourse using the INCEpTION tool and compares manual annotation with automatic approaches based on large language models. The study focuses on sports reports (specifically cricket news) and evaluates the performance of BERT, DistilBERT, and Logistic Regression models in classifying rhetorical relations such as elaboration, contrast, background, and cause-effect. The results show that DistilBERT achieved the highest accuracy, highlighting its potential for efficient discourse relation prediction. This work contributes to the growing intersection of discourse parsing and transformer-based NLP. (This paper was conducted as part of an academic requirement under the supervision of Prof. Dr. Ralf Klabunde, Linguistic Data Science Lab, Ruhr University Bochum.) Keywords: Rhetorical Structure Theory, INCEpTION, BERT, DistilBERT, Discourse Parsing, NLP. |
| title | Annotate Rhetorical Relations with INCEpTION: A Comparison with Automatic Approaches |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.03808 |