activity
20162021
most citedCross-Modal Subspace Learning with Scheduled Adaptive Margin Constraints

9 citations · 13 across the 6 of their papers we have counts for

collaborators

15 papers

cs.MM2021

Assisting News Media Editors with Cohesive Visual Storylines

Gonçalo Marcelino, David Semedo, André Mourão +3

Creating a cohesive, high-quality, relevant, media story is a challenge that news media editors face on a daily basis. This challenge is aggravated by the flood of highly relevant…

cs.CL20211 cited

Knowledge-driven Answer Generation for Conversational Search

Mariana Leite, Rafael Ferreira, David Semedo +1

The conversational search paradigm introduces a step change over the traditional search paradigm by allowing users to interact with search agents in a multi-turn and natural fashio…

cs.IR2021

BERT Embeddings Can Track Context in Conversational Search

Rafael Ferreira, David Semedo, Joao Magalhaes

The use of conversational assistants to search for information is becoming increasingly more popular among the general public, pushing the research towards more advanced and sophis…

cs.IR2021

Open-Domain Conversational Search Assistant with Transformers

Rafael Ferreira, Mariana Leite, David Semedo +1

Open-domain conversational search assistants aim at answering user questions about open topics in a conversational manner. In this paper we show how the Transformer architecture ac…

cs.MM20199 cited

Cross-Modal Subspace Learning with Scheduled Adaptive Margin Constraints

David Semedo, João Magalhães

Cross-modal embeddings, between textual and visual modalities, aim to organise multimodal instances by their semantic correlations. State-of-the-art approaches use maximum-margin m…

cs.MM20193 cited

Diachronic Cross-modal Embeddings

David Semedo, João Magalhães

Understanding the semantic shifts of multimodal information is only possible with models that capture cross-modal interactions over time. Under this paradigm, a new embedding is ne…