nlp

Making BERT stretchy. Semantic Elasticsearch with Sentence Transformers

QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.

Espial is an engine for automated organization and discovery of personal knowledge

Code for EMNLP18 paper "Spherical Latent Spaces for Stable Variational Autoencoders"

A painless way to pick future time.

Implementation of abstractive summarization using LSTM in the encoder-decoder architecture with local attention.

package lingo provides the data structures and algorithms required for natural language processing

Norwegian NLP Resources

Deep contextualized word representations for Chinese

Using pre trained word embeddings (Fasttext, Word2Vec)

A command-line toolkit to extract text content and category data from Wikipedia dump files

semantic analysis using word2vector, doc2vector,lstm and other method. mainly for text similarity analysis.

An implementation in TensorFlow of a convolutional neural network (CNN) to perform sentiment classification on tweets.

A comparison and discussion of different NLP methods for 5-class sentiment classification on the SST-5 dataset.

NAACL'2021: Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240

论文实现(ACL2019)：《Matching the Blanks: Distributional Similarity for Relation Learning》

Lightning Fast Language Prediction 🚀

中文垃圾短信识别(手写分类器)

Lexicon-based Named Entity Recognition

Open solution to the Toxic Comment Classification Challenge

a Fast, Flexible, Extensible and Easy-to-use NLP Large-scale Pretraining and Multi-task Learning Framework.

Helping AI practitioners better understand their datasets and models in text classification. From ServiceNow.

Your Advanced Twitter stalking tool (this used to be cool before LLMs)

Lazy, AI chatbot service.

A web app to create and browse text visualizations for automated customer listening.

Large, curated set of benchmark datasets for evaluating automatic keyphrase extraction algorithms.

第三届魔镜杯 智能客服问题相似性算法设计 第12名解决方案

AMR Parsing as Sequence-to-Graph Transduction

Corpus of Russian news articles collected from Lenta.Ru

RETIRED - OpenSTT is now retired. If you would like more information on Mycroft AI's open source STT projects, please visit:

📄 A repo containing notes and discussions for our weekly NLP/ML paper discussions.

PubMed 200k RCT dataset: a large dataset for sequential sentence classification.

Models for automatic abstractive summarization

Self-training with Weak Supervision (NAACL 2021)

Xcode Playground Sample Code for the Flight School Guide to Swift Strings

🔤 Natural language detection for Elixir without AI

Natural Language Processing Chatbot for RocketChat

(somewhat) cleaned-up notebooks used in researching public comments for FCC Proceeding 17-108 (Net Neutrality Repeal)

Japanese Natural Langauge Processing Libraries

"Bootstrapping Relationship Extractors with Distributional Semantics" (Batista et al., 2015) in EMNLP'15 - Python implementation

Ruby SDK for Dialogflow

Language Lego

Notebooks for the Seattle PyData 2017 talk on Scattertext

Spokestack is a library that allows a user to easily incorporate a voice interface into any Python application with a focus on embedded systems.

Code for the paper "Are Sixteen Heads Really Better than One?"

Unilm for Chinese Chitchat Robot.基于Unilm模型的夸夸式闲聊机器人项目。

Content Enhanced BERT-based Text-to-SQL Generation https://arxiv.org/abs/1910.07179

Solution to Kaggle's Quora Duplicate Question Detection Competition

MATILDA: Multi-AnnoTator multi-language Interactive Lightweight Dialogue Annotator

A baseline implementation for FNC-1