Search Results for author:
Found 16 papers, 10 papers with code
Identifying the Human Values behind Arguments
First experiments with the automatic classification of human values are promising, with F_1-scores up to 0. 81 and 0. 25 on average.
“Mama Always Had a Way of Explaining Things So I Could Understand”: A Dialogue Corpus for Learning to Construct Explanations
As AI is more and more pervasive in everyday life, humans have an increasing demand to understand its behavior and decisions.
Argument Novelty and Validity Assessment via Multitask and Transfer Learning
An argument is a constellation of premises reasoning towards a certain conclusion.
Modeling the Quality of Dialogical Explanations
In this work, we study explanation dialogues in terms of the interactions between the explainer and explainee and how they correlate with the quality of explanations in terms of a successful understanding on the explainee's side.
The Touché23-ValueEval Dataset for Identifying Human Values behind Arguments
We present the Touch\'e23-ValueEval Dataset for Identifying Human Values behind Arguments.
Conclusion-based Counter-Argument Generation
In real-world debates, the most common way to counter an argument is to reason against its main point, that is, its conclusion.
"Mama Always Had a Way of Explaining Things So I Could Understand'': A Dialogue Corpus for Learning to Construct Explanations
As AI is more and more pervasive in everyday life, humans have an increasing demand to understand its behavior and decisions.
The Moral Debater: A Study on the Computational Generation of Morally Framed Arguments
An audience's prior beliefs and morals are strong indicators of how likely they will be affected by a given argument.
Assessing the Sufficiency of Arguments through Conclusion Generation
An argument whose premises make its conclusion rationally worthy to be drawn is called sufficient in argument quality research.
Key Point Analysis via Contrastive Learning and Extractive Argument Summarization
Key point analysis is the task of extracting a set of concise and high-level statements from a given collection of arguments, representing the gist of these arguments.
Generating Informative Conclusions for Argumentative Texts
Third, insights are provided into the suitability of our corpus for the task, the differences between the two generation paradigms, the trade-off between informativeness and conciseness, and the impact of encoding argumentative knowledge.
Argument Undermining: Counter-Argument Generation by Attacking Weak Premises
We hypothesize that identifying the argument's weak premises is key to effective countering.
Belief-based Generation of Argumentative Claims
In this work, we aim to bridge this gap by studying the task of belief-based claim generation: Given a controversial topic and a set of beliefs, generate an argumentative claim tailored to the beliefs.
Target Inference in Argument Conclusion Generation
In particular, we argue here that a decisive step is to infer a conclusion{'}s target, and we hypothesize that this target is related to the premises{'} targets.
Modeling Frames in Argumentation
In general, we call a set of arguments that focus on the same aspect a frame.
