713 citations
- University of LisbonPT78 papers
- Centre National de la Recherche ScientifiqueFR33 papers
- University of OxfordGB28 papers
- Instituto Superior TécnicoPT27 papers
- Sorbonne UniversitéFR27 papers
- European Organization for Nuclear ResearchCH26 papers
- Université Grenoble AlpesFR24 papers
- Charles UniversityCZ23 papers
- Institute of High Energy PhysicsCN23 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR23 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di MilanoIT23 papers
- Karlsruhe Institute of TechnologyDE23 papers
8 papers · 1 filter
ACE-2005-PT: Corpus for Event Extraction in Portuguese
Luís Filipe Cunha, Purificação Silvano, Ricardo Campos +1
Event extraction is an NLP task that commonly involves identifying the central word (trigger) for an event and its associated arguments in text. ACE-2005 is widely recognised as th…
Lisbon Computational Linguists at SemEval-2024 Task 2: Using A Mistral 7B Model and Data Augmentation
Artur Guimarães, Bruno Martins, João Magalhães
This paper describes our approach to the SemEval-2024 safe biomedical Natural Language Inference for Clinical Trials (NLI4CT) task, which concerns classifying statements about Clin…
Onception: Active Learning with Expert Advice for Real World Machine Translation
Vânia Mendonça, Ricardo Rei, Luisa Coheur +1
Active learning can play an important role in low-resource settings (i.e., where annotated data is scarce), by selecting which instances may be more worthy to annotate. Most active…
Question rewriting? Assessing its importance for conversational question answering
Gonçalo Raposo, Rui Ribeiro, Bruno Martins +1
In conversational question answering, systems must correctly interpret the interconnected interactions and generate knowledgeable answers, which may require the retrieval of releva…
Assessing User Expertise in Spoken Dialog System Interactions
Eugénio Ribeiro, Fernando Batista, Isabel Trancoso +3
Identifying the level of expertise of its users is important for a system since it can lead to a better interaction through adaptation techniques. Furthermore, this information can…
A Labeled Graph Kernel for Relationship Extraction
Gonçalo Simões, Helena Galhardas, David Matos
In this paper, we propose an approach for Relationship Extraction (RE) based on labeled graph kernels. The kernel we propose is a particularization of a random walk kernel that exp…