activity
20212024
most citedPrompting as Probing: Using Language Models for Knowledge Base Construction

14 citations · 16 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL2024

Extracting triples from dialogues for conversational social agents

Piek Vossen, Selene Báez Santamaría, Lenka Bajčetić +1

Obtaining an explicit understanding of communication within a Hybrid Intelligence collaboration is essential to create controllable and transparent agents. In this paper, we descri…

cs.CL2023

Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation

Lea Krause, Selene Báez Santamaría, Michiel van der Meer +1

This paper discusses our approaches for task-oriented conversational modelling using subjective knowledge, with a particular emphasis on response generation. Our methodology was sh…

cs.CL2022

Will It Blend? Mixing Training Paradigms & Prompting for Argument Quality Prediction

Michiel van der Meer, Myrthe Reuver, Urja Khurana +2

This paper describes our contributions to the Shared Task of the 9th Workshop on Argument Mining (2022). Our approach uses Large Language Models for the task of Argument Quality Pr…

cs.AI2022

Evaluating Agent Interactions Through Episodic Knowledge Graphs

Selene Báez Santamaría, Piek Vossen, Thomas Baier

We present a new method based on episodic Knowledge Graphs (eKGs) for evaluating (multimodal) conversational agents in open domains. This graph is generated by interpreting raw sig…

cs.CL2022★ 14 cited

Prompting as Probing: Using Language Models for Knowledge Base Construction

Dimitrios Alivanistos, Selene Báez Santamaría, Michael Cochez +3

Language Models (LMs) have proven to be useful in various downstream applications, such as summarisation, translation, question answering and text classification. LMs are becoming…

cs.HC2021★ 2 cited

EMISSOR: A platform for capturing multimodal interactions as Episodic Memories and Interpretations with Situated Scenario-based Ontological References

Selene Báez Santamaría, Thomas Baier, Taewoon Kim +3

We present EMISSOR: a platform to capture multimodal interactions as recordings of episodic experiences with explicit referential interpretations that also yield an episodic Knowle…