mitjanikolaus

a-PyTorch-Tutorial-to-Image-Captioning

Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning

amdtk

arctic-captions

childes-communicative-feedback

Code for Communicative Feedback corpus analyses on CHILDES. Work published at CogSci 2022 and 2023.

childes-speech-acts

compositional-image-captioning

Code for the CoNLL 2019 paper "Compositional Generalization in Image Captioning" by Mitja Nikolaus, Mostafa Abdou, Matthew Lamm, Rahul Aralikatte and Desmond Elliott

emergent_communication

Code for the ICLR 2024 paper Emergent Communication with Conversational Repair by Mitja Nikolaus.

ldr-template

Latex template for the journal "Language Development Research"

multimodal-predicate-noun-dependencies

Code for the EMNLP 2022 paper "Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?" by Mitja Nikolaus, Emmanuelle Salin, Stephane Ayache, Abdellah Fourtassi, and Benoit Favre.

perception-and-production-based-learning

Code for the CoNLL 2021 paper "Modeling the Interaction Between Perception-Based and Production-Based Learning in Children’s Early Acquisition of Semantic Knowledge" by Mitja Nikolaus and Abdellah Fourtassi

mitjanikolaus/compositional-image-captioning

Code for the CoNLL 2019 paper "Compositional Generalization in Image Captioning" by Mitja Nikolaus, Mostafa Abdou, Matthew Lamm, Rahul Aralikatte and Desmond Elliott

mitjanikolaus/childes-speech-acts

mitjanikolaus/ldr-template

Latex template for the journal "Language Development Research"

mitjanikolaus/multimodal-predicate-noun-dependencies

Code for the EMNLP 2022 paper "Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?" by Mitja Nikolaus, Emmanuelle Salin, Stephane Ayache, Abdellah Fourtassi, and Benoit Favre.

mitjanikolaus/perception-and-production-based-learning

Code for the CoNLL 2021 paper "Modeling the Interaction Between Perception-Based and Production-Based Learning in Children’s Early Acquisition of Semantic Knowledge" by Mitja Nikolaus and Abdellah Fourtassi

mitjanikolaus/childes-communicative-feedback

Code for Communicative Feedback corpus analyses on CHILDES. Work published at CogSci 2022 and 2023.

mitjanikolaus/emergent_communication

Code for the ICLR 2024 paper Emergent Communication with Conversational Repair by Mitja Nikolaus.

mitjanikolaus/childespy

mitjanikolaus/childes-grammaticality

mitjanikolaus/childesr

R interface to childes-db

mitjanikolaus/clip2brain

Code from paper "Natural language supervision with a large and diverse dataset builds better models of human high-level visual cortex"

mitjanikolaus/CPC_audio

An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.

mitjanikolaus/cross-situational-learning-abstract-scenes

Code for the CMCL 2021 paper "Evaluating the Acquisition of Semantic Knowledge from Cross-situational Learning in Artificial Neural Networks" by Mitja Nikolaus and Abdellah Fourtassi

mitjanikolaus/EGG

EGG: Emergence of lanGuage in Games

mitjanikolaus/evaluation-pipeline

Evaluation pipeline for the BabyLM Challenge 2023.

mitjanikolaus/evaluation-pipeline-2024

The evaluation pipeline for the 2024 BabyLM Challenge.

mitjanikolaus/Lis_internship_BC

mitjanikolaus/multimodal-predicate-noun-dependencies-data

mitjanikolaus/multimodal_seq2seq_gSCAN

The multi-modal sequence to sequence baseline neural models used in the Grounded SCAN paper.

mitjanikolaus/Oscar

Oscar and VinVL

mitjanikolaus/peppa

mitjanikolaus/peppa-paper

Peppa cartoon paper

mitjanikolaus/pylangacq

Language Acquisition Research Tools in Python

mitjanikolaus/UNITER

Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"

mitjanikolaus/UnMasked

Score masked language models on grammar test suites

mitjanikolaus/vilbert-multi-task

Multi Task Vision and Language

mitjanikolaus/ViLT

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

mitjanikolaus/VL-BERT

Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".

mitjanikolaus/volta

Code and data for the framework in "Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs", TACL 2021.

mitjanikolaus/zerospeech2021_baseline

BERT and LSTM baseline models of the ZeroSpeech Challenge 2021