Pinned Repositories
BLEnD
BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages
crossembeddings-twitter
emoji_modifiers
*sem paper 2018 - models and code
LMMS
Language Modelling Makes Sense - WSD (and more) with Contextual Embeddings
meemi
NLP-progress
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.
OD-SentiMP-21
preproc-textclassification
relative
Repository to learn relation vectors from text corpora. Includes the implementation and pre-trained embeddings of the RELATIVE model from the IJCAI 2019 paper "A Latent Variable Model for Learning Distributional Relation Vectors".
rwe
Repository containing data and code of the ACL-19 paper "Relational Word Embeddings"
pedrada88's Repositories
pedrada88/crossembeddings-twitter
pedrada88/rwe
Repository containing data and code of the ACL-19 paper "Relational Word Embeddings"
pedrada88/preproc-textclassification
pedrada88/relative
Repository to learn relation vectors from text corpora. Includes the implementation and pre-trained embeddings of the RELATIVE model from the IJCAI 2019 paper "A Latent Variable Model for Learning Distributional Relation Vectors".
pedrada88/NLP-progress
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.
pedrada88/BLEnD
BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages
pedrada88/emoji_modifiers
*sem paper 2018 - models and code
pedrada88/LMMS
Language Modelling Makes Sense - WSD (and more) with Contextual Embeddings
pedrada88/meemi
pedrada88/OD-SentiMP-21
pedrada88/pilehvar.github.io
pedrada88/tner
T-NER is a python tool to analyse language model finetuning on named-entity-recognition (NER). It has an easy interface to finetune models, test on cross-domain datasets, where we compile 9 publicly available NER datasets. Models can be deployed immediately on our web app for qualitative analysis, and the API for a micro service. Also we release all the NER model checkpoints, where the most generalized model trained on all the dataset, has 43 entity types.
pedrada88/vecmap
A framework to learn cross-lingual word embedding mappings