Demos

• A pytorch demonstration of a trained ARAE model
• Fashion meets Computer Science and Natural Language Processing
• Translating text to a virtual world (MUSE)
• Generation of games from text (TERENCE)
• Automated semantic annotation of textual stories (TERENCE)
• Automated semantic annotation of video (AMASS++)
• Talk2Car demo

Datasets and Software

• Automatic detection and correction of context-dependent dt-mistakes using neural networks
• Temporal Information Extraction by Predicting Relative Time-lines
• Evaluating textual representations through image generation
• Do Neural Network Cross-Modal Mappings Really Bridge Modalities?
• Word-Level Loss Extensions for Neural Temporal Relation Classification
• Imagined Visual Representations as Multimodal Embeddings
• The cultural image captioning datasets in Sheng et.al (2019)
• A dataset for multimodal question answering in the cultural heritage domain
• Talk2Car : Giving commands to self-driving cars
• Towards Extracting Absolute Event Timelines from English Clinical Reports
• Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning
• DAME platform for natural language processing:
• Semantic role labeling
• Deep learning approach
• Traditional model using feature engineering
• Bilingual Lexicon Induction Classifier
• Structured Learning for Temporal Relation Extraction
• The Amazon dresses dataset used in Zoghbi et al. (2016) and Laenen et al. (2018)
• Bilingual Latent Dirichlet Allocation (BiLDA)
• Latent words language model
• Spatial role labeling
• TempEval2-Adjudicated
• Wikipedia article Barack Obama with TIMEX3
• FABLES AND STORYDATASET (MUSE)

If you have any question with regard to the software that was developed in the LIIR group, please contact prof. Marie-Francine Moens.