Adversarial training and data augmentation for neural question-answering models
KitanaQA: Adversarial training and data augmentation for neural question-answering models.
A large medical text dataset curated for abbreviation disambiguation
Repository for Medical Dataset for Abbreviation Disambiguation for Natural Language Understanding (MeDAL)
A text-to-speech conversion library in Python
pyttsx3 is a text-to-speech conversion library in Python. Unlike alternative libraries, it works offline.
Generate questions and summaries for your texts
Input your text and get questions and summaries in return!
Scanning Single Shot Detector for Math in Document Images
A PyTorch implementation of ScanSSD Scanning Single Shot MultiBox Detector by Parag Mali. It was developed using SSD implementation by Max deGroot.
BERT for Joint Intent Classification and Slot Filling
(Unofficial) Pytorch implementation of JointBERT: BERT for Joint Intent Classification and Slot Filling.
Birds of a Feather, from Statistical Descriptors to Parametric Models
"Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models."
Blazing speed using a T5 version implemented in ONNX
Summarization, translation, Q&A, text generation and more at blazing speed using a T5 version implemented in ONNX.
A programming library for clustering text
Carrot2 is a programming library for clustering text. It can automatically discover groups of related documents and label them with short key terms or phrases.
A python framework designed to compute features from speech files
python freamework to extract features from speech.
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
Marius Mosbach, Maksym Andriushchenko, Dietrich Klakow
A pre-trained language model for English Tweets
A pre-trained language model for English Tweets.
A toolkit that provides a off-the-shelf framework to implement lots of NLP extraction tasks
OpenUE is an open-source toolkit that provides a off-the-shelf framework to implement lots of NLP extraction tasks.
An open source audio annotation tool
Open source audio annotation tool for humans
A python toolkit to work with text-based dataset quickly and effortlessly
Texthero is very simple to learn and designed to be used on top of Pandas.
Semantic Search using sentence embeddings from Transformers models and others
Simple application using sentece embedding to project the documents in a high dimensional space and find most similarities using cosine similarity.
Using transformers to predict next word and predict mask word
Simple application using transformers models to predict next word or a masked word in a sentence.
Compares embedding vectors for two different texts visually and by numerical metrics
Compares embedding vectors for two different texts visually and by numerical metrics.
A fast and user-friendly tool for transformer inference on CPU and GPU
make transformers serving fast by adding a turbo to your inference engine!
Question Answering using Albert and Electra using wikipedia text as context
Question Answering using Albert and Electra.