Papers by Agnieszka Falenska
“Feels Feminine to Me”: Understanding Perceived Gendered Style through Human Annotations (2025.emnlp-main)
Copied to clipboard
| Challenge: | Using gender identity-based framing, language–gender associations are often grounded in the author’s gender identity, inferred from their language use. |
| Approach: | They propose to operationalize the language–gender association as a perceived gender expression of language, focusing on how expression is externally interpreted by humans, independent of the author’s gender identity. |
| Outcome: | The first dataset of itskind identifies 5,100 human annotations of perceived gendered style—human-written texts rated on a five-point scale from very feminine to very masculine. |
Gender Identity in Pretrained Language Models: An Inclusive Approach to Data Creation and Probing (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained language models encode binary gender information of text authors, raising the risk of skewed representations and downstream harms. |
| Approach: | They use a corpus of YouTube transcripts from transgender, cisgender and non-binary speakers to examine whether pretrained language models encode binary gender information. |
| Outcome: | The proposed model encodes gender information for all gender identities but to different extents. |
GRAIN-S: Manually Annotated Syntax for German Interviews (2020.lrec-1)
Copied to clipboard
| Challenge: | GRAIN-S is a set of manually created syntactic annotations for radio interviews in germany. |
| Approach: | They propose to use GRAIN-S to create syntactic annotations for radio interviews in germany. |
| Outcome: | The proposed dataset extends an existing corpus GRAIN and comes with constituency and dependency trees for six interviews. |
Self-reported Demographics and Discourse Dynamics in a Persuasive Online Forum (2024.lrec-main)
Copied to clipboard
| Challenge: | Research on language as interactive discourse demonstrates the deliberate use of demographic parameters such as gender, ethnicity, and class to shape social identities. |
| Approach: | They propose to investigate the role and effects of gender self-disclosures on online discourse dynamics by focusing on author gender. |
| Outcome: | The proposed dataset will provide a further impulse for research on the interplay between gender disclosures, community interaction, and persuasion in online discourse. |
How-to Guides for Specific Audiences: A Corpus and Initial Findings (2023.acl-srw)
Copied to clipboard
| Challenge: | wikiHow guides for specific target groups reflect disparate social norms and subtle stereotypes, a new study shows . wikihow guides are subject to subtle biases, and we aim to raise awareness of these inequalities in future work. |
| Approach: | They investigate the extent to which how-to guides from wikiHow differ in practice depending on intended audience. |
| Outcome: | The findings show that how-to guides from wikiHow differ in practice depending on the intended audience. |
Moving TIGER beyond Sentence-Level (L18-1)
Copied to clipboard
| Challenge: | TIGER 2.2-doc is a new set of annotations for the German TIger corpus. |
| Approach: | They propose a new set of annotations for the German TIGER corpus . they introduce new document-level annotations: authors and their gender. |
| Outcome: | The new annotations improve the TIGER corpus and its structure and authors and gender. |
“I understand your perspective”: LLM Persuasion through the Lens of Communicative Action Theory (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can generate high-quality arguments, yet their ability to engage in nuanced and persuasive communicative actions remains largely unexplored. |
| Approach: | They examine whether Large Language Models express illocutionary intent in ways comparable to human communication by simulated online discussions . |
| Outcome: | The proposed models express illocutionary intents in ways comparable to human communication, and crowd-sourced workers prefer them over human-written ones. |
German Radio Interviews: The GRAIN Release of the SFB732 Silver Standard Collection (L18-1)
Copied to clipboard
Katrin Schweitzer, Kerstin Eckart, Markus Gärtner, Agnieszka Falenska, Arndt Riester, Ina Rösiger, Antje Schweitzer, Sabrina Stehwien, Jonas Kuhn
| Challenge: | GRAIN contains German radio interviews and is annotated on multiple linguistic layers. |
| Approach: | They present GRAIN as part of the SFB732 Silver Standard Collection . GRAIN contains German radio interviews and is annotated on multiple linguistic layers . |
| Outcome: | The GRAIN data set contains German radio interviews and is annotated on multiple linguistic layers. |
The (Non-)Utility of Structural Features in BiLSTM-based Dependency Parsers (P19-1)
Copied to clipboard
| Challenge: | Existing non-neural dependency parsers benefit from information coming from structural features . however, their successors lack explicit information about the structural context . |
| Approach: | They propose to model the structural context of a biLSTM-based dependency parser with features built from partial subtrees. |
| Outcome: | The proposed models do not use any conventional structural features but capture implicitly the structural context. |
AI Argues Differently: Distinct Argumentative and Linguistic Patterns of LLMs in Persuasive Contexts (2025.emnlp-main)
Copied to clipboard
| Challenge: | Distinguishing LLM-generated text from human-written is a key challenge for safe and ethical NLP, especially in high-stake settings such as persuasive online discourse. |
| Approach: | They propose to use general-purpose linguistic features and domain-specific features related to argument quality to compare human- and LLM-authored arguments. |
| Outcome: | The proposed framework compares arguments by humans and three LLMs using two easily-interpretable feature sets. |
IMSurReal: IMS at the Surface Realization Shared Task 2019 (D19-63)
Copied to clipboard
| Challenge: | a system for shallow and deep completion is presented for the Surface Realization Shared Task 2019 . the system achieves state-of-the-art performance without using external data. |
| Approach: | They propose a surface realization system that takes five steps without external data . they perform detailed error analysis revealing correlation between word order freedom and difficulty . |
| Outcome: | The proposed system achieves state-of-the-art without external data . it achieves highest BLEU scores on tokenized text and human evaluation on four languages . |
Please note that I’m just an AI: Analysis of Behavior Patterns of LLMs in (Non-)offensive Speech Identification (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are becoming a part of our everyday lives by being used as tools for information search, content creation, writing assistance, and many more. |
| Approach: | They propose to use Large Language Models to detect offensive online language in applications with social risk, such as late-life companions and online content moderators. |
| Outcome: | The proposed models fail to detect offensive language and are therefore unsuitable for use in social applications such as late-life companions and online content moderators. |