Iacer Calixto

visualsem. Repository for VisualSem: a high-quality knowledge graph to support research in vision and language.

MultimodalNMT. Multi-modal Neural Machine Translation in PyTorch

variational_mmt. Code base for the paper "Latent variable model for multi-modal translation".

butd-image-captioning. Bottom-up Top-down image captioning model with PyTorch.

visualsem-kg. Representation learning for VisualSem knowledge graph.

wiki_crosslingual. Code to reproduce the NAACL 2021 paper "Wikipedia entities as rendezvous across languages: grounding multilingual LMs by predicting wikipedia hyperlinks".

multilingual-multimodal-embedding. Train and use sentence-level multilingual and multi-modal embeddings.

iacercalixto.github.io. Professional website.

FLPM. Fuzzy Linear Programming Model for OD matrix estimation

mme-positive-examples-mse. Multimodal embeddings (vision+text) using mean squared error as training criteria.

coreference_resolution. Coreference resolution project in natural language processing.

WALS. Python