SBERT studies meaning representations: Decomposing sentence embeddings into explainable semantic features
Models based on large-pretrained language models, such as S (entence) BERT, provide
effective and efficient sentence embeddings that show high correlation to human similarity …
effective and efficient sentence embeddings that show high correlation to human similarity …
Natural language decompositions of implicit content enable better text representations
When people interpret text, they rely on inferences that go beyond the observed language
itself. Inspired by this observation, we introduce a method for the analysis of text that takes …
itself. Inspired by this observation, we introduce a method for the analysis of text that takes …
Noam Chomsky at SemEval-2023 task 4: Hierarchical similarity-aware model for human value detection
S Honda, S Wilharm - … of the 17th International Workshop on …, 2023 - aclanthology.org
This paper presents a hierarchical similarity-aware approach for the SemEval-2023 task 4
human value detection behind arguments using SBERT. The approach takes similarity score …
human value detection behind arguments using SBERT. The approach takes similarity score …
[PDF][PDF] Making the Implicit Explicit: Implicit Content as a First Class Citizen in NLP.
Abstract Language is multifaceted. A given utterance can be re-expressed in equivalent
forms, and its implicit and explicit content support various logical and pragmatic inferences …
forms, and its implicit and explicit content support various logical and pragmatic inferences …
Nudging Towards Responsible Recommendations: a Graph-Based Approach to Mitigate Belief Filter Bubbles
Personalized recommendation systems homogenize user preferences, causing an extreme
belief imbalance and aggravating user bias. This phenomenon is known as the filter bubble …
belief imbalance and aggravating user bias. This phenomenon is known as the filter bubble …
Metrics of Graph-Based Meaning Representations with Applications from Parsing Evaluation to Explainable NLG Evaluation and Semantic Search
J Opitz - 2024 - archiv.ub.uni-heidelberg.de
" Who does what to whom?" The goal of a graph-based meaning representation (in short:
MR) is to represent the meaning of a text in a structured format. With an MR, we can …
MR) is to represent the meaning of a text in a structured format. With an MR, we can …
[图书][B] The Pragmatics of Governmental Discourse: Resilience, Sustainability and Wellbeing
AY Gupta - 2024 - books.google.com
This book presents a novel methodological framework for analysing governmental
discourse. It involves combining pragmatist perspectives on language with computational …
discourse. It involves combining pragmatist perspectives on language with computational …
Balancing Information Perception with Yin-Yang: Agent-Based Information Neutrality Model for Recommendation Systems
While preference-based recommendation algorithms effectively enhance user engagement
by recommending personalized content, they often result in the creation of``filter bubbles'' …
by recommending personalized content, they often result in the creation of``filter bubbles'' …
A Hybrid Human-AI Approach for Argument Map Creation From Transcripts
L Anastasiou, A De Liddo - Proceedings of the First Workshop on …, 2024 - aclanthology.org
In order to overcome challenges of traditional deliberation approaches that often silo
information exchange between synchronous and asynchronous modes therefore hindering …
information exchange between synchronous and asynchronous modes therefore hindering …
Computational Argumentation Approaches to Improve Sensemaking and Evidence-based Reasoning in Online Deliberation Systems
L Anastasiou - 2023 - oro.open.ac.uk
Deliberation is the process through which communities identify potential solutions for a
problem and select the solution that most effectively meets their diverse requirements …
problem and select the solution that most effectively meets their diverse requirements …