Papers by Kai Eckert
ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing statistical phrasal or hierarchical machine translation systems relies on a large set of translation rules which results in engineering challenges. |
| Approach: | They propose to use factorized grammar from the field of linguistics as more general translation rules from XTAG English Grammar to generate a manually crafted summarization dataset. |
| Outcome: | The proposed method outperforms existing methods on low-resource language translation tasks with less training data. |
Investigating the Role of Argumentation in the Rhetorical Analysis of Scientific Publications with Neural Multi-Task Learning Models (D18-1)
Copied to clipboard
| Challenge: | Scientific publications are argumentative and often adhere to well-trodden rhetorical patterns and argumentation schemes. |
| Approach: | They investigate the link between scientific publications and rhetorical aspects such as discourse categories or citation contexts by coupling rhetorical classifiers with extraction of argumentative components. |
| Outcome: | The proposed models show significant performance gains for different rhetorical analysis tasks. |
GenGO: ACL Paper Explorer with Semantic Features (2024.acl-demos)
Copied to clipboard
| Challenge: | Scholarly document processing (SDP) is a powerful tool for researchers to process knowledge stored in research papers. |
| Approach: | They propose a system that allows researchers to search papers published in ACL conferences with metadata and text embeddings. |
| Outcome: | The proposed system is simple and efficient to reduce maintenance and financial costs and is extensible to support open development and transparency. |
ROUGE-K: Do Your Summaries Have Keywords? (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing evaluation metrics for extreme summarization models do not pay explicit attention to keywords in summaries, leaving developers ignorant of their presence. |
| Approach: | They propose a keyword-oriented evaluation metric, dubbed ROUGE-K, which quantifies how well summaries include keywords. |
| Outcome: | The proposed model can be extended to include more keywords while keeping the overall quality. |