Achtung:

Sie haben Javascript deaktiviert!
Sie haben versucht eine Funktion zu nutzen, die nur mit Javascript möglich ist. Um sämtliche Funktionalitäten unserer Internetseite zu nutzen, aktivieren Sie bitte Javascript in Ihrem Browser.

Paderborn University in February 2023 Show image information

Paderborn University in February 2023

Photo: Paderborn University, Hannah Brauckhoff

Maja Stahl

Contact
Publications
 Maja Stahl

Computational Social Science

Member - Former

Office:
ZM2.A.03.11
Visitor:
Zukunftsmeile 2
33102 Paderborn

Open list in Research Information System

2023

Identifying Feedback Types to Augment Feedback Comment Generation

M. Stahl, H. Wachsmuth, in: Proceedings of the 16th International Natural Language Generation Conference, 2023

In the context of language learning, feedback comment generation is the task of generating hints or explanatory notes for learner texts that help understand why a part of text is erroneous. This paper presents our approach to the Feedback Comment Generation Shared Task, collocated with the 16th International Natural Language Generation Conference (INLG 2023). The approach augments the generation of feedback comments by a self-supervised identification of feedback types in a multitask-learning setting. Within the shared task, other approaches performed more effective, yet the combined modeling of feedback type classification and feedback comment generation is superior to performing feedback generation only.


2022

Argument Novelty and Validity Assessment via Multitask and Transfer Learning

M. Alshomary, M. Stahl, in: Proceedings of the 9th Workshop on Argument Mining, International Conference on Computational Linguistics, 2022, pp. 111–114

An argument is a constellation of premises reasoning towards a certain conclusion. The automatic generation of conclusions is becoming a very prominent task, raising the need for automatic measures to assess the quality of these generated conclusions. The SharedTask at the 9th Workshop on Argument Mining proposes a new task to assess the novelty and validity of a conclusion given a set of premises. In this paper, we present a multitask learning approach that transfers the knowledge learned from the natural language inference task to the tasks at hand. Evaluation results indicate the importance of both knowledge transfer and joint learning, placing our approach in the fifth place with strong results compared to baselines.


To Prefer or to Choose? Generating Agency and Power Counterfactuals Jointly for Gender Bias Mitigation

M. Stahl, M. Spliethöver, H. Wachsmuth, in: Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science, 2022

Gender bias may emerge from an unequal representation of agency and power, for example, by portraying women frequently as passive and powerless ("She accepted her future'') and men as proactive and powerful ("He chose his future''). When language models learn from respective texts, they may reproduce or even amplify the bias. An effective way to mitigate bias is to generate counterfactual sentences with opposite agency and power to the training. Recent work targeted agency-specific verbs from a lexicon to this end. We argue that this is insufficient, due to the interaction of agency and power and their dependence on context. In this paper, we thus develop a new rewriting model that identifies verbs with the desired agency and power in the context of the given sentence. The verbs' probability is then boosted to encourage the model to rewrite both connotations jointly. According to automatic metrics, our model effectively controls for power while being competitive in agency to the state of the art. In our evaluation, human annotators favored its counterfactuals in terms of both connotations, also deeming its meaning preservation better.


Open list in Research Information System

The University for the Information Society