Search Results for author: Sebastian Martschat

Found 10 papers, 3 papers with code

Multi-Source (Pre-)Training for Cross-Domain Measurement, Unit and Context Extraction

1 code implementation5 Aug 2023 Yueling Li, Sebastian Martschat, Simone Paolo Ponzetto

We present a cross-domain approach for automated measurement and context extraction based on pre-trained language models.

Domain Generalization

Improving ROUGE for Timeline Summarization

no code implementations EACL 2017 Sebastian Martschat, Katja Markert

Current evaluation metrics for timeline summarization either ignore the temporal aspect of the task or require strict date matching.

Semantic Similarity Semantic Textual Similarity +1

Latent Structures for Coreference Resolution

no code implementations TACL 2015 Sebastian Martschat, Michael Strube

Machine learning approaches to coreference resolution vary greatly in the modeling of the problem: while early approaches operated on the mention pair level, current research focuses on ranking architectures and antecedent trees.

BIG-bench Machine Learning coreference-resolution +2

Cannot find the paper you are looking for? You can Submit a new open access paper.