Predicting Stance Change Using Modular Architectures
Aldo Porco,Dan Goldwasser +1 more
- pp 396-406
Reads0
Chats0
TLDR
A modular learning approach is suggested, which decomposes the task into multiple modules, focusing on different aspects of the interaction between users, their beliefs, and the arguments they are exposed to.Abstract:
The ability to change a person’s mind on a given issue depends both on the arguments they are presented with and on their underlying perspectives and biases on that issue. Predicting stance changes require characterizing both aspects and the interaction between them, especially in realistic settings in which stance changes are very rare. In this paper, we suggest a modular learning approach, which decomposes the task into multiple modules, focusing on different aspects of the interaction between users, their beliefs, and the arguments they are exposed to. Our experiments show that our modular approach archives significantly better results compared to the end-to-end approach using BERT over the same inputs.read more
Citations
More filters
Posted Content
Scientia Potentia Est -- On the Role of Knowledge in Computational Argumentation
Iryna Gurevych,Anne Lauscher,Henning Wachsmuth,Gordon L. Houston,Iryna Gurevych,Goran Glavaš +5 more
TL;DR: This paper proposed a pyramid of types of knowledge required in computational argumentation, briefly discussing the role and integration of these types in the field, and outlining the main challenges for future work.
Journal ArticleDOI
Scientia Potentia Est—On the Role of Knowledge in Computational Argumentation
Iryna Gurevych,Gordon L. Houston +1 more
TL;DR: The authors provide a taxonomy of types of knowledge required in computational argumentation tasks, and discuss the four main research areas in CA, and outline and discuss directions for future research efforts.
Posted Content
STEM: Unsupervised STructural EMbedding for Stance Detection
TL;DR: The authors proposed an unsupervised and domain-independent framework for stance detection in multi-participant discussion, which constructs the interaction network from which they derive topological embeddings for each speaker and divide the speakers into stance-partitions.
Journal ArticleDOI
STEM: Unsupervised STructural EMbedding for Stance Detection
TL;DR: This article proposed an unsupervised and domain-independent framework for stance detection in multi-participant discussion, which constructs the interaction network from which they derive topological embedding for each speaker and divide the speakers into stance-partitions.
References
More filters
Proceedings ArticleDOI
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TL;DR: BERT as mentioned in this paper pre-trains deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
Journal Article
Natural Language Processing (Almost) from Scratch
TL;DR: A unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity recognition, and semantic role labeling is proposed.
Book
Persuasive Technology: Using Computers to Change What We Think and Do
TL;DR: Mother Nature knows best--How engineered organizations of the future will resemble natural-born systems.
Journal ArticleDOI
Liberals and Conservatives Rely on Different Sets of Moral Foundations
TL;DR: Across 4 studies using multiple methods, liberals consistently showed greater endorsement and use of the Harm/care and Fairness/reciprocity foundations compared to the other 3 foundations, whereas conservatives endorsed and used the 5 foundations more equally.
Book
Persuasive technology : using computers to change what we think and do
TL;DR: Fogg has coined the phrase Captology (an acronym for computers as persuasive technologies) to capture the domain of research, design, and applications of persuasive computers as mentioned in this paper, and has revealed how Web sites, software applications, and mobile devices can be used to change people's attitudes and behavior.