Papers by Aleksandra Gabryszak
TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for Relation Extraction (RE) still show a high error rate . label errors account for 8% absolute F1 test error, and more than 50% of examples need to be relabeled. |
| Approach: | They validate the most challenging 5K examples using trained annotators and analyze misclassifications on the challenging instances. |
| Outcome: | The proposed methods perform well on the most challenging datasets and improve on the relabeled test set. |
Large Language Models Are Echo Chambers (2024.lrec-main)
Copied to clipboard
Jan Nehring, Aleksandra Gabryszak, Pascal Jürgens, Aljoscha Burchardt, Stefan Schaffer, Matthias Spielkamp, Birgit Stark
| Challenge: | Modern large language models and chatbots are subject to criticism in many aspects. |
| Approach: | They show that large language models and chatbots are echo chambers . they annotate inputs and show that all chatbot agree . |
| Outcome: | The proposed models show that they tend to agree with the opinions of their users. |
A German Corpus for Fine-Grained Named Entity Recognition and Relation Extraction of Traffic and Industry Events (L18-1)
Copied to clipboard
Martin Schiersch, Veselina Mironova, Maximilian Schmitt, Philippe Thomas, Aleksandra Gabryszak, Leonhard Hennig
| Challenge: | Using text streams to extract events pertaining to specific companies, routes and routes remains a challenge. |
| Approach: | They describe a corpus of German-language documents annotated with fine-grained geo-entities and standard named entity types. |
| Outcome: | The proposed corpus consists of newswire texts, twitter messages, and traffic reports from radio stations, police and railway companies. |
A Corpus Study and Annotation Schema for Named Entity Recognition and Relation Extraction of Business Products (L18-1)
Copied to clipboard
| Challenge: | Existing annotation guidelines for non-standard entity types and relations are lacking in news and forum texts. |
| Approach: | They propose a corpus study and an annotation schema for the annotation of product entity and company-product relation mentions. |
| Outcome: | The proposed annotation schema and guidelines are applied to the annotation of product entities and company-product relation mentions. |
Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Neural relation extraction models capture linguistic and semantic properties of the input, a recent study shows. |
| Approach: | They introduce 14 probing tasks targeting linguistic properties relevant to RE . they add contextualized word representations to enhance probing performance . |
| Outcome: | The proposed models achieve state-of-the-art on two datasets, TACRED and SemEval 2010 Task 8 . they show that the models capture linguistic and semantic properties relevant to the downstream task . |