nlp

NLP pipeline using word2vec (preprocessing/embedding/prediction/clustering)

[EMNLP 2019] Mixture Content Selection for Diverse Sequence Generation (Question Generation / Abstractive Summarization)

My solution to Kaggle Quora Question Pairs competition (Top 2%, Private LB log loss 0.13497).

Code for NAACL 2019 paper: Distant Supervision Relation Extraction with Intra-Bag and Inter-Bag Attentions

TOEIC(Test of English for International Communication) solving using pytorch-pretrained-BERT model.

On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines

自注意力与文本分类

This is a list of open-source projects at Microsoft Research NLP Group

Accelerated NLP pipelines for fast inference on CPU. Built with Transformers and ONNX runtime.

PyTorch Language Model for 1-Billion Word (LM1B / GBW) Dataset

Streaming tweets with spark, language detection & sentiment analysis, dashboard with Kibana

Unofficial implementation of Perceiver IO

Multilingual Retrieval on Yelp Search Engine ⚡

English-French Machine Language Translation in Tensorflow

A PureScript, browser-based implementation of LDA topic modeling.

Interpretable Models for NLP using PyTorch

NLP framework in python for entity recognition and relationship extraction

A collection of PyTorch notebooks for learning and practicing deep learning

Text summarizer for golang using LexRank

FoLiA Linguistic Annotation Tool -- Flat is a web-based linguistic annotation environment based around the FoLiA format (http://proycon.github.io/foli...

Source code for "Head-Driven Phrase Structure Grammar Parsing on Penn Treebank" published at ACL 2019

R wrapper for fastText

The Self-dialogue Corpus - a collection of self-dialogues across music, movies and sports

Botfuel SDK to build highly conversational chatbots

One million English sentences, each split into two sentences that together preserve the original meaning, extracted from Wikipedia edits.

A natural language event parser for java and android.

Applying NLP transfer learning techniques to predict Tweet stance toward a topic

R package to Embed All the Things! using StarSpace

[AKBC 19] Improving Relation Extraction by Pre-trained Language Representations

Lemmatizer for text in English. Inspired by Python's nltk.corpus.reader.wordnet.morphy

Build AI-powered semantic search applications in JavaScript

Big Data Analytics Using Interactive Workflows

PyTorch tutorials A to Z

Uses a distributed word representation to finds words along the hyperchord of two input words.

Implementation of ULMFit algorithm for text classification via transfer learning

Tensorflow and Keras implementation of the state of the art researches in Dialog System NLU

Relation Extraction using Deep learning(CNN)

Excel Integration with spaCy. Training NER using Excel/XLSX from PDF, DOCX, PPT, PNG or JPG.

NLP research experiments, built on PyTorch within the AllenNLP framework.

Methods about Deep Learning for Text Matching

:no_entry: ARCHIVED :no_entry: Accesses the Monkeylearn API for Text Classifiers and Extractors

Make it easier to compare and cross-reference the names of companies and people by applying strong normalisation.

This is where I put all my work in Natural Language Processing

Cross-Lingual Alignment of Contextual Word Embeddings

Tokenizers and lemmatizers for Go

LockeBot: a demonstration of implementing a basic question answering bot with use of Rasa and a database

Implementation of algorithm in keyword extraction,including TextRank,TF-IDF and the combination of both

document classification using LSTM + self attention

word2vec++ is a Distributed Representations of Words (word2vec) library and tools implementation, written in C++11 from the scratch

:pencil2: Hunspell extension for spaCy 2.0.