Papers by Eva Maria Vecchi

8 papers
Argument Quality Assessment in the Age of Instruction-Following Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Argument quality assessment is critical for opinion formation, decision making, writing education, and the like.
Approach: They propose to use large language models to leverage knowledge across contexts to enable a much more reliable assessment.
Outcome: The proposed approach improves the quality of argumentation and the ability to leverage knowledge across contexts.
Node Placement in Argument Maps: Modeling Unidirectional Relations in High & Low-Resource Scenarios (2023.acl-long)

Copied to clipboard

Challenge: Argument maps structure discourse into nodes with each node being an argument that supports or opposes its parent argument.
Approach: They propose a task of node placement: suggesting candidate nodes as parents for a new contribution.
Outcome: The proposed method improves the quality of the argument maps and reduces redundancy.
It Is Not Only the Negative that Deserves Attention! Understanding, Generation & Evaluation of (Positive) Moderation (2025.naacl-long)

Copied to clipboard

Challenge: Moderation is essential for maintaining and improving the quality of online discussions.
Approach: They annotate a dataset on 13 modes of discussion and use it to generate positive moderation.
Outcome: The proposed model shows that professional moderation generates higher ratings than professional moderated moderation, but prefers professional moderate in pairwise comparison.
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.
Mining, Assessing, and Improving Arguments in NLP and the Social Sciences (2024.lrec-tutorials)

Copied to clipboard

Challenge: a tutorial on computational argumentation is updated to address the problem of argument quality . argument quality is a field of interdisciplinary research that connects natural language processing to social sciences .
Approach: They present an updated version of the EACL 2023 tutorial on argument quality . they will focus on the notions of argument quality across disciplines .
Outcome: The updated version of the EACL 2023 tutorial focuses on argument quality assessment . the authors will focus on the interface between Argument Mining and Deliberation Theory .
Mining, Assessing, and Improving Arguments in NLP and the Social Sciences (2023.eacl-tutorials)

Copied to clipboard

Challenge: a tutorial on argument quality assessment will focus on what makes an argument good or bad . argument quality is a field encompassing varying tasks on the automated analysis and synthesis of natural language arguments.
Approach: This tutorial will focus on the assessment of argument quality across disciplines . authors will involve participants in annotation studies on the quality assessment .
Outcome: The tutorial will focus on the assessment of argument quality across disciplines . it will involve participants in two annotation studies on the quality assessment and the improvement of quality .
Towards Argument Mining for Social Good: A Survey (2021.acl-long)

Copied to clipboard

Challenge: Argument Mining is a social science-based approach to analysis and analysis of arguments.
Approach: They propose a novel definition of argument quality which integrates the social science literature and the argument quality.
Outcome: The proposed definition of argument quality integrates the social science literature and the argument quality debate.
PerspectiveMod: A Perspectivist Resource for Deliberative Moderation (2025.emnlp-main)

Copied to clipboard

Challenge: Human moderators in online discussions face a heterogeneous range of tasks that go beyond content moderation, or policing.
Approach: They propose a dataset of online comments annotated for the question "Does this comment require moderation?" they aim to improve discussion quality by analyzing annotator perspectives and annotating their views.
Outcome: The proposed model is unique in its intentional variation across the level of moderation experience embedded in the source data, the annotator profiles and the individuality of the annnotator.

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