-
Faculty of Sciences - University of Lisbon
Highlights
- Pro
Stars
Convert Machine Learning Code Between Frameworks
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Named Entity Recognition (LSTM + CRF) - Tensorflow
Official implementations for various pre-training models of ERNIE-family, covering topics of Language Understanding & Generation, Multimodal Understanding & Generation, and beyond.
Incremental learning of word embeddings with context informativeness.
Source code for "A Lightweight Recurrent Network for Sequence Modeling"
**Archived** Epic is a high performance statistical parser written in Scala, along with a framework for building complex structured prediction models.
Spoken Language Understanding(SLU)/Slot Filling in Keras
Linguistically-Informed Self-Attention implemented in TensorFlow
A system for generating training labels via natural language explanations
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
BabyAI platform. A testbed for training agents to understand and execute language commands.
Deep neural models for core NLP tasks (Pytorch version)
An implementation of Chinese Whispers in Python.
scikit-learn: machine learning in Python
Library for fast text representation and classification.
A minimal, pure Python library to interface with CoNLL-U format files.
TensorFlow code and pre-trained models for BERT
Automatically exported from code.google.com/p/word2vec
Software in C and data files for the popular GloVe model for distributed word representations, a.k.a. word vectors or embeddings
Towards a Model of Prediction-based Syntactic Category Acquisition: First Steps with Word Embeddings. Sixth Workshop on Cognitive Aspects of Computational Language Learning (CogACLL 2015).
Unsupervised Semantic Frame Induction using Triclustering
Code and data for the NAACL 2018 article "Multimodal Frame Identification with Multilingual Evaluation" by Botschen et al