Papers by Marieke van Erp

5 papers
Re-evaluating the Tomes for the Times (2024.lrec-main)

Copied to clipboard

Challenge: Literature is to some degree a snapshot of the time it was written and the societal attitudes of the period.
Approach: They exploit known text co-occurrence metrics to identify problematic descriptors . they propose a method for making explicit such problematic associations .
Outcome: The proposed method could be used by publishing houses, libraries and organisations concerned with social justice to make explicit such problematic associations.
Comparing Annotated Datasets for Named Entity Recognition in English Literature (2022.lrec-1)

Copied to clipboard

Challenge: Generally speaking, the majority of NER tools struggle to perform well when the entities in the text contain specific characteristics.
Approach: They analysed two existing annotated datasets and two additional gold standard datasets to evaluate the performance of two NER tools.
Outcome: The results show that the performance of two NER tools varies significantly depending on the gold standard used for the individual evaluations.
Towards Entity Spaces (2020.lrec-1)

Copied to clipboard

Challenge: Entities are a central element of knowledge bases and are used in many knowledge-centric tasks including text analysis.
Approach: They propose to use entity spaces to represent a set of associated entities with near-identity to provide a handle to an amorphous grouping of entities.
Outcome: The proposed representations improve recall of entity linking in English by using disambiguation pages.
Tracking Textual Similarities in Neo-Latin Drama Networks (2022.lrec-1)

Copied to clipboard

Challenge: a wide international network of exchanges between writers of different nationalities is characteristic of the early Modern Era.
Approach: They describe the first experiments to track the inter-national network of text reuse within the Early Modern community of Neo-Latin humanists.
Outcome: The results show that the early Modern writers and writers are part of a wider, universal, intellectual community.
It’s All About the Confidence: An Unsupervised Approach for Multilingual Historical Entity Linking using Large Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Existing approaches to EL for historical texts require substantial training data or rely on domain-specific rules that limit scalability.
Approach: They propose an unsupervised ensemble approach combining a Small Language Model and an LLM for historical EL.
Outcome: The proposed approach outperforms state-of-the-art models on four established benchmarks in six European languages from the 19th and 20th centuries.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations