Papers by Diego Moussallem

5 papers
LOLA – An Open-Source Massively Multilingual Large Language Model (2025.coling-main)

Copied to clipboard

Challenge: Using a sparse Mixture-of-Experts Transformer architecture, our model is highly efficient and efficient across languages.
Approach: They propose a multilingual large language model trained on more than 160 languages using a sparse Mixture-of-Experts Transformer architecture.
Outcome: The proposed model performs well on natural language generation and understanding tasks while avoiding the common pitfalls of multilinguality.
LIdioms: A Multilingual Linked Idioms Data Set (L18-1)

Copied to clipboard

Challenge: Recent studies have focused on linguistic data sets that are bilingual on the Linguistic Linked Open Data (LLOD) 1 .
Approach: They describe a multilingual RDF representation of idioms currently containing five languages . they use a model to structure the data and a method to link the data to well-known multilingual data sets such as BabelNet.
Outcome: The proposed model complies with best practices according to Linguistic Linked Open Data Community.
RDF2PT: Generating Brazilian Portuguese Texts from RDF Data (L18-1)

Copied to clipboard

Challenge: Existing approaches to generate natural language from RDF data have been proposed to generate texts in Brazilian Portuguese.
Approach: They propose a rule-based approach to verbalize RDF data to Brazilian Portuguese language.
Outcome: The proposed approach generates text similar to that generated by humans and can hence be easily understood.
Contextual Augmentation for Entity Linking using Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Entity Linking involves detecting and linking entity mentions in natural language texts to a knowledge graph.
Approach: They propose a fine-tuned model that integrates entity recognition and disambiguation in a unified framework.
Outcome: The proposed model achieves state-of-the-art on out-of domain datasets and compares with baselines.
NeuralREG: An end-to-end approach to referring expression generation (P18-1)

Copied to clipboard

Challenge: Referring Expression Generation models typically rely on features such as salience and grammatical function to make decisions about form and content.
Approach: They propose a new approach that makes decisions about form and content in one go . they use a delexicalized version of the WebNLG corpus to test the approach .
Outcome: The proposed approach significantly improves over two strong baselines.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations