Sebastian Martschat


2023

pdf bib
Multi-Source (Pre-)Training for Cross-Domain Measurement, Unit and Context Extraction
Yueling Li | Sebastian Martschat | Simone Paolo Ponzetto
The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks

We present a cross-domain approach for automated measurement and context extraction based on pre-trained language models. We construct a multi-source, multi-domain corpus and train an end-to-end extraction pipeline. We then apply multi-source task-adaptive pre-training and fine-tuning to benchmark the cross-domain generalization capability of our model. Further, we conceptualize and apply a task-specific error analysis and derive insights for future work. Our results suggest that multi-source training leads to the best overall results, while single-source training yields the best results for the respective individual domain. While our setup is successful at extracting quantity values and units, more research is needed to improve the extraction of contextual entities. We make the cross-domain corpus used in this work available online.

2018

pdf
A Temporally Sensitive Submodularity Framework for Timeline Summarization
Sebastian Martschat | Katja Markert
Proceedings of the 22nd Conference on Computational Natural Language Learning

Timeline summarization (TLS) creates an overview of long-running events via dated daily summaries for the most important dates. TLS differs from standard multi-document summarization (MDS) in the importance of date selection, interdependencies between summaries of different dates and by having very short summaries compared to the number of corpus documents. However, we show that MDS optimization models using submodular functions can be adapted to yield well-performing TLS models by designing objective functions and constraints that model the temporal dimension inherent in TLS. Importantly, these adaptations retain the elegance and advantages of the original MDS models (clear separation of features and inference, performance guarantees and scalability, little need for supervision) that current TLS-specific models lack.

2017

pdf
Dynamic Entity Representations in Neural Language Models
Yangfeng Ji | Chenhao Tan | Sebastian Martschat | Yejin Choi | Noah A. Smith
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Understanding a long document requires tracking how entities are introduced and evolve over time. We present a new type of language model, EntityNLM, that can explicitly model entities, dynamically update their representations, and contextually generate their mentions. Our model is generative and flexible; it can model an arbitrary number of entities in context while generating each entity mention at an arbitrary length. In addition, it can be used for several different tasks such as language modeling, coreference resolution, and entity prediction. Experimental results with all these tasks demonstrate that our model consistently outperforms strong baselines and prior work.

pdf
Improving ROUGE for Timeline Summarization
Sebastian Martschat | Katja Markert
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers

Current evaluation metrics for timeline summarization either ignore the temporal aspect of the task or require strict date matching. We introduce variants of ROUGE that allow alignment of daily summaries via temporal distance or semantic similarity. We argue for the suitability of these variants in a theoretical analysis and demonstrate it in a battery of task-specific tests.

2015

pdf
Plug Latent Structures and Play Coreference Resolution
Sebastian Martschat | Patrick Claus | Michael Strube
Proceedings of ACL-IJCNLP 2015 System Demonstrations

pdf
Latent Structures for Coreference Resolution
Sebastian Martschat | Michael Strube
Transactions of the Association for Computational Linguistics, Volume 3

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. We propose a unified representation of different approaches to coreference resolution in terms of the structure they operate on. We represent several coreference resolution approaches proposed in the literature in our framework and evaluate their performance. Finally, we conduct a systematic analysis of the output of these approaches, highlighting differences and similarities.

pdf bib
Analyzing and Visualizing Coreference Resolution Errors
Sebastian Martschat | Thierry Göckel | Michael Strube
Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations

2014

pdf
Recall Error Analysis for Coreference Resolution
Sebastian Martschat | Michael Strube
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2013

pdf
Multigraph Clustering for Unsupervised Coreference Resolution
Sebastian Martschat
51st Annual Meeting of the Association for Computational Linguistics Proceedings of the Student Research Workshop

2012

pdf
A Multigraph Model for Coreference Resolution
Sebastian Martschat | Jie Cai | Samuel Broscheit | Éva Mújdricza-Maydt | Michael Strube
Joint Conference on EMNLP and CoNLL - Shared Task